© 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. 7-RESID-POST-AA
    11. 59343
    Prev
    Next
    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fluorescence
    -0.07
    .Te
    -0.07
     nrows
    -0.07
    建设用地
    -0.07
    <|im_start|>
    -0.07
    -padding
    -0.07
    效益
    -0.07
     absentee
    -0.07
     multiplying
    -0.07
     backyard
    -0.07
    POSITIVE LOGITS
    itta
    0.07
    مصطف
    0.06
     Brief
    0.06
    ipped
    0.06
    探访
    0.06
    orf
    0.06
    ENCIES
    0.06
    .Unique
    0.06
     militias
    0.06
    _featured
    0.06
    Activations Density 0.359%

    No Known Activations