© 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. 108181
    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
    myModal
    -0.25
     Euros
    -0.23
    AndUpdate
    -0.23
    天河
    -0.23
    ä¸Ĭåįĩ
    -0.23
    /she
    -0.23
     none
    -0.23
     between
    -0.23
    è¿ĩå¾Ĺ
    -0.23
    abouts
    -0.22
    POSITIVE LOGITS
    ester
    0.28
    ç»ĵ
    0.27
    ner
    0.27
     Blades
    0.26
     Broadcast
    0.25
    eness
    0.25
    osterone
    0.25
    att
    0.25
    MAR
    0.25
     broadcast
    0.25
    Activations Density 7.215%

    No Known Activations

    This feature has no known activations.