© 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. 12-TRANSCODER-HP
    7. 22965
    Prev
    Next
    INDEX
    Explanations

    Raspberry Pi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    箸
    -0.29
    onChange
    -0.27
    refixer
    -0.27
    大涨
    -0.25
    istro
    -0.25
    æĭħä¿Ŀ
    -0.24
    æľīæĦıä¹ī
    -0.23
    iceps
    -0.23
    åݨ
    -0.23
    åĪĴç®Ĺ
    -0.23
    POSITIVE LOGITS
     pinch
    0.28
    _();↵
    0.27
    %)↵↵
    0.26
     denies
    0.26
    *)↵↵
    0.26
    ç§ijæĬĢèĤ¡ä»½
    0.26
    *D
    0.25
    %'↵
    0.25
     parted
    0.25
    /tab
    0.25
    Activations Density 0.005%

    No Known Activations