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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2723
    Prev
    Next
    INDEX
    Explanations

    als

    np_max-act · gemini-2.0-flash

    the neuron detects capitalized proper names/brand or publication titles (named entities).

    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
     ])↵↵
    -0.07
    ()))
↵
    -0.07
    "D
    -0.07
    盈利
    -0.07
     MouseEvent
    -0.06
    .bo
    -0.06
    -0.06
     ).↵↵
    -0.06
    fine
    -0.06
     uninstall
    -0.06
    POSITIVE LOGITS
    쳐
    0.07
    Ensure
    0.07
     której
    0.07
    rch
    0.07
    ㉱
    0.06
    组织领导
    0.06
    .EntityFramework
    0.06
    秘书长
    0.06
     RCC
    0.06
    urança
    0.06
    Activations Density 0.173%

    No Known Activations