© 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. 130268
    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
    depend
    -0.29
    ä¸Ģ代
    -0.27
    Ã¶ÄŁ
    -0.26
    OF
    -0.26
    å¥Ĺ
    -0.25
    leck
    -0.24
    座
    -0.24
     côté
    -0.23
     Nullable
    -0.23
     Pik
    -0.23
    POSITIVE LOGITS
     kindly
    0.25
    ìĭ±
    0.24
    vere
    0.23
    Ton
    0.23
     flags
    0.23
     purs
    0.23
     Extr
    0.23
     nth
    0.23
     sake
    0.23
    æıIJåıĸ
    0.23
    Activations Density 7.371%

    No Known Activations

    This feature has no known activations.