© 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. 63953
    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
    çīĻ
    -0.31
    缺
    -0.30
    æݬ
    -0.26
    kos
    -0.26
    å¿ĥæĦ¿
    -0.26
    æĿĵ
    -0.25
     æŁ¥
    -0.25
    ä¸Ģ声
    -0.25
    æŁ¥éĺħ
    -0.25
     conveniently
    -0.24
    POSITIVE LOGITS
    rapper
    0.32
     collateral
    0.24
    ÙĦÙĦ
    0.24
    ìł¯
    0.24
    æ¹ĥ
    0.24
     ani
    0.24
    립
    0.24
    started
    0.24
    oÄŁlu
    0.24
    RESSED
    0.24
    Activations Density 3.770%

    No Known Activations

    This feature has no known activations.