© 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. 121385
    Prev
    Next
    INDEX
    Explanations

    _modules

    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_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
     assh
    -0.07
     waged
    -0.07
    umble
    -0.07
     fighter
    -0.06
    _skin
    -0.06
    创造出
    -0.06
     proceedings
    -0.06
     ä
    -0.06
     pulp
    -0.06
    /Game
    -0.06
    POSITIVE LOGITS
     Apostle
    0.07
    Sphere
    0.07
     PAR
    0.07
    quiries
    0.07
     colonies
    0.06
     OC
    0.06
    .land
    0.06
     refreshToken
    0.06
    monthly
    0.06
     Waterloo
    0.06
    Activations Density 0.000%

    No Known Activations