© 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. 108289
    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
    å¾Ĥ
    -0.27
    ildo
    -0.27
     Recap
    -0.26
    å¤ļå¹´çļĦ
    -0.25
     Pik
    -0.25
    sweet
    -0.24
    åij¨å¹´
    -0.24
     lip
    -0.24
    bare
    -0.24
    ean
    -0.24
    POSITIVE LOGITS
    mentation
    0.29
    lyph
    0.27
    ç±
    0.27
    TINGS
    0.26
    éĶĢ
    0.26
     discrim
    0.25
     gy
    0.24
     wash
    0.24
    TRAN
    0.24
    ายà¸Ļ
    0.24
    Activations Density 2.163%

    No Known Activations

    This feature has no known activations.