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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 42346
    Prev
    Next
    INDEX
    Explanations

    About senators

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quo
    -0.30
    gment
    -0.27
    <Unit
    -0.27
    ao
    -0.26
     astr
    -0.25
     floor
    -0.25
    quo
    -0.24
    è§ľ
    -0.24
     bi
    -0.24
    ç¦ģ
    -0.24
    POSITIVE LOGITS
     TAS
    0.25
    ernals
    0.25
     Yas
    0.24
    UNDER
    0.24
    road
    0.24
     spectator
    0.24
    ä¸ĭæīĭ
    0.24
    tring
    0.24
    VIC
    0.24
    èĩªæĿ¥æ°´
    0.23
    Activations Density 0.005%

    No Known Activations