© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    6. 93343
    Prev
    Next
    INDEX
    Explanations

    bakeries and baked goods

    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
     Lua
    -0.07
     Sudoku
    -0.07
    cash
    -0.06
    .spacing
    -0.06
     sâu
    -0.06
    ERVER
    -0.06
    encryption
    -0.06
    .decrypt
    -0.06
     REPRESENT
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    手艺
    0.08
    .projects
    0.08
    \s
    0.07
     bf
    0.07
    �
    0.07
    	rs
    0.07
    _persona
    0.07
    _reaction
    0.07
    志强
    0.07
    干警
    0.07
    Activations Density 0.087%

    No Known Activations