© 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. 31-TRANSCODER-HP
    7. 19119
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guard
    -0.31
    XObject
    -0.30
     Lan
    -0.28
    æĸ¯çī¹
    -0.27
    nist
    -0.26
    (StringUtils
    -0.26
    Guard
    -0.25
    æĸ°éĹ»åıijå¸ĥ
    -0.25
    éŸ
    -0.25
     Tart
    -0.25
    POSITIVE LOGITS
    odon
    0.29
    è¶ħé¢Ŀ
    0.26
     Fortune
    0.26
    åĪĨæł¡
    0.25
    è¶ħåĩº
    0.25
    æľ¬å±Ĭ
    0.25
     //~
    0.24
     sympathy
    0.24
    hausen
    0.24
    ennes
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.