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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2087
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
     номер
    -0.08
    惬
    -0.07
    ":"/
    -0.07
    (Abstract
    -0.07
    uber
    -0.07
    สอน
    -0.07
    룻
    -0.07
    寓意
    -0.07
    宾馆
    -0.06
     Datagram
    -0.06
    POSITIVE LOGITS
    .geom
    0.07
     técnica
    0.07
     kỹ
    0.07
     Fifty
    0.07
     За
    0.07
     кол
    0.06
    -how
    0.06
    🔭
    0.06
     во
    0.06
     until
    0.06
    Activations Density 0.034%

    No Known Activations