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. 30067
    Prev
    Next
    INDEX
    Explanations

    __

    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
    コーヒー
    -0.07
    丕
    -0.06
     competitive
    -0.06
     Ella
    -0.06
    Cause
    -0.06
     skeptical
    -0.06
    城
    -0.06
    Eine
    -0.06
     Contribution
    -0.06
    asive
    -0.06
    POSITIVE LOGITS
    [input
    0.08
    )._
    0.07
    animate
    0.07
    );↵↵↵
    0.07
    しました
    0.06
    加之
    0.06
    �이
    0.06
    ******↵
    0.06
    /.↵↵
    0.06
    няти
    0.06
    Activations Density 0.003%

    No Known Activations