© 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. 142079
    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
    å¹¿æ³ĽçļĦ
    -0.27
    _scenario
    -0.25
    Gs
    -0.24
    åıįä¹ĭ
    -0.24
    客æĪ·æıIJä¾Ľ
    -0.24
    inel
    -0.24
    åıįåĵį
    -0.24
    å½¢æĪIJçļĦ
    -0.23
    oref
    -0.23
    FileStream
    -0.23
    POSITIVE LOGITS
    çļĦèĥ½éĩı
    0.28
     NDEBUG
    0.27
    Ñĩе
    0.26
     Faster
    0.26
    ç¢į
    0.25
     Abel
    0.25
    bur
    0.25
     Leaving
    0.25
     resemble
    0.25
    áf
    0.25
    Activations Density 3.423%

    No Known Activations

    This feature has no known activations.