© 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. 20-TRANSCODER-HP
    7. 141930
    Prev
    Next
    INDEX
    Explanations

    single-digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    秣
    -0.26
    ãĤīãģı
    -0.26
    berman
    -0.25
    çĶŁäº§èĥ½åĬĽ
    -0.25
    è´
    -0.25
    /configuration
    -0.25
    uchs
    -0.24
    .ViewModel
    -0.24
    -su
    -0.24
    AMS
    -0.24
    POSITIVE LOGITS
    æ´¾åĩº
    0.26
    çļĨ
    0.25
    viz
    0.25
    BJECT
    0.25
    aget
    0.25
    ffee
    0.24
    изм
    0.24
    ÑĨев
    0.24
    ç¢İçīĩ
    0.24
    ç½ķè§ģ
    0.24
    Activations Density 9.843%

    No Known Activations