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. 87133
    Prev
    Next
    INDEX
    Explanations

    Afghanistan

    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
    地坪
    -0.07
    秀丽
    -0.07
    ﰙ
    -0.07
     EDUC
    -0.07
     TextField
    -0.07
    游击
    -0.06
    和地区
    -0.06
    绵阳
    -0.06
    分辨率
    -0.06
    英国
    -0.06
    POSITIVE LOGITS
    angers
    0.07
    acional
    0.06
    Signals
    0.06
    Girls
    0.06
    (Function
    0.06
    حكوم
    0.06
    ᲂ
    0.06
    ients
    0.06
    ión
    0.06
    规章
    0.06
    Activations Density 0.012%

    No Known Activations