© 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. 108213
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åĵ¨
    -0.27
     Cath
    -0.25
    ContentType
    -0.25
     microphone
    -0.25
    band
    -0.25
    æĹ¥åľ¨
    -0.25
     бÑĥд
    -0.24
    ings
    -0.24
     Tamb
    -0.24
     dap
    -0.23
    POSITIVE LOGITS
    è¿Ļæł·åģļ
    0.32
    ominator
    0.28
    åľ¨è¿Ļæĸ¹éĿ¢
    0.24
    代
    0.24
    //===
    0.23
    è¿Ļä¹Īåģļ
    0.23
    iffies
    0.23
    å«©
    0.23
    æĸ¯å¡Ķ
    0.23
    è¡Įæĥħ
    0.23
    Activations Density 13.779%

    No Known Activations

    This feature has no known activations.