© 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. 18-TRANSCODER-HP
    7. 89518
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    วา
    -0.29
    ç¢
    -0.28
    LOGGER
    -0.26
    _vars
    -0.26
    rawl
    -0.25
     Reconstruction
    -0.25
    nos
    -0.25
     CI
    -0.24
    avo
    -0.24
    hausen
    -0.24
    POSITIVE LOGITS
     offsetof
    0.32
    cem
    0.28
    溯æºIJ
    0.28
    ulary
    0.27
    &p
    0.26
     histoire
    0.25
    ä¸İä¸ŃåĽ½
    0.25
    opc
    0.24
    对æİ¥
    0.24
    æIJľç´¢
    0.24
    Activations Density 0.041%

    No Known Activations

    This feature has no known activations.