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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 25659
    Prev
    Next
    INDEX
    Explanations

    and

    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
     endorse
    -0.07
    的日子
    -0.07
    *******************************************************************************/↵
    -0.07
    GetType
    -0.07
    صن
    -0.07
    ,"\
    -0.06
     설정
    -0.06
     Canary
    -0.06
     singapore
    -0.06
    _aut
    -0.06
    POSITIVE LOGITS
     Echo
    0.08
    海边
    0.07
    Pie
    0.07
     rever
    0.07
     ange
    0.07
    ycz
    0.06
    YSTEM
    0.06
    Fonts
    0.06
    iras
    0.06
    уль
    0.06
    Activations Density 0.012%

    No Known Activations