© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 126423
    Prev
    Next
    INDEX
    Explanations

    Abbreviations

    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
    游泳
    -0.07
    💊
    -0.07
    作者本人
    -0.07
    国债
    -0.07
    uppet
    -0.07
    狀
    -0.06
     vomiting
    -0.06
    oh
    -0.06
    Виде
    -0.06
     pertaining
    -0.06
    POSITIVE LOGITS
    --------↵
    0.08
     intensive
    0.07
    hausen
    0.07
     INTERVAL
    0.07
    .Views
    0.07
    allocated
    0.06
     occupy
    0.06
     Nelson
    0.06
    .transitions
    0.06
    碛
    0.06
    Activations Density 0.017%

    No Known Activations