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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RESID-POST-AA
    11. 92737
    Prev
    Next
    INDEX
    Explanations

    learning and understanding

    np_max-act · gemini-2.0-flash

    The neuron detects language that signals academic or scientific discussion.

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .force
    -0.07
    .ObjectMapper
    -0.07
    bulk
    -0.07
    _force
    -0.07
    Won
    -0.06
    tracks
    -0.06
    퍠
    -0.06
    അ
    -0.06
     unsustainable
    -0.06
    揽
    -0.06
    POSITIVE LOGITS
    -files
    0.07
     aprove
    0.07
    ève
    0.07
    .DATA
    0.07
     ContentView
    0.07
    _alg
    0.07
     América
    0.07
    .Cdecl
    0.07
    RYPTO
    0.06
    ,nonatomic
    0.06
    Activations Density 2.292%

    No Known Activations