© 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. 11-RESID-POST-AA
    11. 129683
    Prev
    Next
    INDEX
    Explanations

    Buildup of unwanted material

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     strokes
    -0.08
    腾
    -0.07
    汽车
    -0.07
    槐
    -0.07
     blanks
    -0.07
    所得
    -0.07
    高速
    -0.07
    Menu
    -0.07
    letters
    -0.07
    ቶ
    -0.07
    POSITIVE LOGITS
    的世界
    0.07
     Subscriber
    0.07
    iat
    0.07
     제가
    0.07
     gehören
    0.07
     McCorm
    0.07
     Martian
    0.07
     Cos
    0.07
    的地方
    0.06
     IPCC
    0.06
    Activations Density 0.061%

    No Known Activations