© 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. 60474
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    话剧
    -0.07
    Dispose
    -0.07
     ומת
    -0.07
    .cap
    -0.07
     progress
    -0.07
     Chess
    -0.06
     peacefully
    -0.06
     issu
    -0.06
    _U
    -0.06
    意識
    -0.06
    POSITIVE LOGITS
    ="$
    0.07
     Firearms
    0.07
    菜肴
    0.07
    츙
    0.07
    obsług
    0.07
    杨欢
    0.07
    ArrayType
    0.07
    :@{
    0.06
    �
    0.06
    .JSONArray
    0.06
    Activations Density 0.051%

    No Known Activations