© 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. 23790
    Prev
    Next
    INDEX
    Explanations

    Spider

    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
    cip
    -0.30
     tán
    -0.28
    ACLE
    -0.27
    [,]
    -0.26
    å¹Ĥ
    -0.25
    egis
    -0.24
    å·¥ä¸ļ大åѦ
    -0.24
    è·º
    -0.24
    ónica
    -0.23
    Ø·ÙĬ
    -0.23
    POSITIVE LOGITS
    ä¸Ģç±»
    0.27
    hill
    0.27
     componentDidMount
    0.25
     pr
    0.25
    hausen
    0.25
    idth
    0.25
    æĹ¢
    0.24
     Neither
    0.24
    ”;
    0.24
    ä¸Ģæł·
    0.24
    Activations Density 0.005%

    No Known Activations