© 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. 19-RESID-POST-AA
    11. 71056
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Avalanche
    -0.07
    -console
    -0.07
    BOOLE
    -0.07
    אפליק
    -0.07
    منتدي
    -0.07
    YSTICK
    -0.07
    _float
    -0.07
    匮
    -0.07
    importDefault
    -0.07
    ㎚
    -0.06
    POSITIVE LOGITS
     by
    0.09
    .can
    0.07
     לשמור
    0.07
    etailed
    0.07
    greater
    0.07
    secondary
    0.07
    ĥ
    0.07
    guided
    0.07
    Bill
    0.07
    (cfg
    0.07
    Activations Density 0.093%

    No Known Activations