© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142411
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific terminology

    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
    åł¡
    -0.28
    OrElse
    -0.25
    åĵªå®¶
    -0.25
    æĭĦ
    -0.25
    StatusLabel
    -0.25
    ument
    -0.24
    stitial
    -0.24
    геÑĢ
    -0.24
    è¿Ľ
    -0.24
     Darling
    -0.24
    POSITIVE LOGITS
    æĮģ
    0.27
     ?>&
    0.27
     grunt
    0.25
    缮åħī
    0.25
    çļĦ缮åħī
    0.24
    /mit
    0.24
    çŃīæĸ¹éĿ¢çļĦ
    0.24
    (gt
    0.24
     Expedition
    0.23
    vation
    0.23
    Activations Density 56.073%

    No Known Activations