© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 118819
    Prev
    Next
    INDEX
    Explanations

    problems/complaints

    np_max-act · gemini-2.0-flash

    the neuron responds to salient content words — nouns, adjectives and other topic-bearing tokens (proper nouns and descriptive terms).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sig
    -0.08
    (shell
    -0.07
     Mitt
    -0.06
     quitting
    -0.06
     Hex
    -0.06
    逍
    -0.06
    纽
    -0.06
     super
    -0.06
     }}>↵
    -0.06
    _OUT
    -0.06
    POSITIVE LOGITS
    像个
    0.09
     dollar
    0.08
    paginate
    0.08
    .JsonProperty
    0.07
    \Backend
    0.07
     policym
    0.07
    -rights
    0.07
    Attention
    0.07
    讦
    0.07
    とにか
    0.07
    Activations Density 0.333%

    No Known Activations