© 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. 63378
    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
    æ´¥
    -0.26
    .setup
    -0.25
     Proper
    -0.25
    åĻ´
    -0.23
     properly
    -0.23
    ampo
    -0.23
    MSG
    -0.23
    ä¸įåºĶ该
    -0.23
    ONENT
    -0.23
    ä¸įåħģ许
    -0.23
    POSITIVE LOGITS
     supplier
    0.27
     responsável
    0.26
    ä¸ºæł¸å¿ĥçļĦ
    0.25
    uez
    0.25
    erness
    0.25
    alse
    0.24
    èµĦäº§è´ŁåĢº
    0.24
     longest
    0.23
    orce
    0.23
     кÑĢÑĥ
    0.23
    Activations Density 26.788%

    No Known Activations

    This feature has no known activations.