© 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. 4977
    Prev
    Next
    INDEX
    Explanations

    graphical models, causal inference

    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
     cấp
    -0.07
     Associated
    -0.07
    保鲜
    -0.07
    (android
    -0.07
     sẵn
    -0.07
    aph
    -0.07
    忠
    -0.07
     letter
    -0.07
     gfx
    -0.07
    imit
    -0.07
    POSITIVE LOGITS
    צוע
    0.07
    .gwt
    0.07
    示意
    0.07
    omething
    0.07
     сли
    0.07
    ॠ
    0.07
    imeo
    0.07
    粒
    0.07
    TRGL
    0.06
    أعضاء
    0.06
    Activations Density 0.008%

    No Known Activations