Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 116596
    Prev
    Next
    INDEX
    Explanations

    message

    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
     Guzzle
    -0.07
    突发
    -0.07
     ham
    -0.07
     params
    -0.07
     Manus
    -0.07
    头部
    -0.07
    ảng
    -0.07
    /Admin
    -0.06
    历史悠久
    -0.06
     LastName
    -0.06
    POSITIVE LOGITS
    的办法
    0.07
     ){
    ↵
    0.07
    );*/↵
    0.07
    overrides
    0.07
    flies
    0.07
    	If
    0.06
    �
    0.06
    lip
    0.06
    闺蜜
    0.06
    *******
    0.06
    Activations Density 0.001%

    No Known Activations