© 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. 63538
    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
    ãĥĿãĥ³
    -0.29
    ean
    -0.29
    á»ĵ
    -0.28
    壳
    -0.28
     complete
    -0.27
    ắn
    -0.26
     convention
    -0.26
    足
    -0.26
    complete
    -0.26
     abolition
    -0.25
    POSITIVE LOGITS
    living
    0.29
     subsequ
    0.28
     Living
    0.28
     literals
    0.27
     infinit
    0.27
    ä½ıæĪ·
    0.26
    Living
    0.26
    -space
    0.25
    æĸ°æĿIJæĸĻ
    0.25
    éħĿ
    0.25
    Activations Density 0.883%

    No Known Activations

    This feature has no known activations.