© 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. 141794
    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
    stell
    -0.31
    STRACT
    -0.28
    æ¶Īæŀģ
    -0.26
    apan
    -0.25
    amm
    -0.25
     snapping
    -0.24
     impl
    -0.24
    ete
    -0.23
    collapsed
    -0.23
    ACCESS
    -0.23
    POSITIVE LOGITS
     BigInt
    0.26
    orate
    0.24
     YYS
    0.24
    è¿Ļ家åħ¬åı¸
    0.24
     Liqu
    0.24
    yers
    0.24
    çªĹåı£
    0.23
     Libre
    0.23
    ffer
    0.23
    ений
    0.23
    Activations Density 36.542%

    No Known Activations

    This feature has no known activations.