© 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. 18089
    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
    =~
    -0.07
     sitios
    -0.07
     �
    -0.07
    ordin
    -0.07
     explanatory
    -0.07
    发病
    -0.07
    .execSQL
    -0.07
    一篇
    -0.06
    尽早
    -0.06
    的地
    -0.06
    POSITIVE LOGITS
     mẽ
    0.08
     كبيرة
    0.07
     cửa
    0.07
    担心
    0.07
    Chem
    0.07
    用微信扫
    0.06
    目睹
    0.06
    Mur
    0.06
     demon
    0.06
     mojo
    0.06
    Activations Density 0.004%

    No Known Activations