© 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. 108327
    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
    EDGE
    -0.25
    xDF
    -0.23
    HING
    -0.23
    terdam
    -0.23
    使ä¹ĭ
    -0.23
    fos
    -0.23
    CAS
    -0.23
    DF
    -0.23
     intern
    -0.23
     occasion
    -0.23
    POSITIVE LOGITS
    æĸ°æ¨¡å¼ı
    0.27
    lama
    0.27
    æľīæľŁ
    0.25
    éĢı
    0.24
    Stars
    0.24
    ù
    0.23
     McGr
    0.22
    èĻļå¼±
    0.22
    umbs
    0.22
    iamond
    0.22
    Activations Density 15.914%

    No Known Activations

    This feature has no known activations.