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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 22884
    Prev
    Next
    INDEX
    Explanations

    continuous functions in mathematics

    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
     Rugby
    -0.07
    >").
    -0.07
    :key
    -0.07
    'es
    -0.07
     Hed
    -0.06
    .Typed
    -0.06
    Grey
    -0.06
     Teh
    -0.06
     hacia
    -0.06
    Coffee
    -0.06
    POSITIVE LOGITS
    ≈
    0.07
    rum
    0.06
    힝
    0.06
     /*↵
    0.06
    .setStyleSheet
    0.06
    톰
    0.06
    王某
    0.06
     kl
    0.06
    און
    0.06
    actal
    0.06
    Activations Density 0.034%

    No Known Activations