© 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. 3886
    Prev
    Next
    INDEX
    Explanations

    code

    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
    NING
    -0.07
    _GAP
    -0.07
    不行
    -0.06
    晓
    -0.06
    AE
    -0.06
    whelming
    -0.06
    핼
    -0.06
    都不是
    -0.06
     кред
    -0.06
     pros
    -0.06
    POSITIVE LOGITS
     regulatory
    0.07
    综合利用
    0.07
     Fog
    0.07
     tilt
    0.07
     permite
    0.06
    ilation
    0.06
    (Matrix
    0.06
    任务
    0.06
     unavoid
    0.06
    רצון
    0.06
    Activations Density 2.396%

    No Known Activations