© 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. 141778
    Prev
    Next
    INDEX
    Explanations

    Numbers and quantities

    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
    олоÑģ
    -0.28
     Clim
    -0.27
    undler
    -0.27
     Doyle
    -0.26
    ä¿Ŀ
    -0.25
    _fonts
    -0.25
    atos
    -0.25
    LineWidth
    -0.25
    深度
    -0.24
    ä¸įåħĭ
    -0.24
    POSITIVE LOGITS
    åĽĽç§į
    0.44
     quadrant
    0.43
    åĽĽä¸ª
    0.43
    corner
    0.42
    åĽĽä½į
    0.41
     four
    0.41
     corner
    0.38
     combinations
    0.38
     quadr
    0.37
     quatre
    0.36
    Activations Density 12.956%

    No Known Activations