© 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. 17759
    Prev
    Next
    INDEX
    Explanations

    academic papers

    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
    ittest
    -0.07
     betray
    -0.07
     Pins
    -0.07
    laughs
    -0.06
    bind
    -0.06
     ambit
    -0.06
     gulp
    -0.06
    סים
    -0.06
    (ByVal
    -0.06
    总资产
    -0.06
    POSITIVE LOGITS
    赛区
    0.07
     County
    0.07
     оказа
    0.07
     outras
    0.07
     county
    0.07
    段
    0.07
    .margin
    0.07
    lineno
    0.07
    ова
    0.07
    海淀
    0.07
    Activations Density 0.023%

    No Known Activations