© 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. 89164
    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
    uda
    -0.26
    baugh
    -0.25
    mund
    -0.24
    èģļ
    -0.24
     threading
    -0.24
    æ¥ŀ
    -0.24
     times
    -0.23
    ived
    -0.23
     smoothed
    -0.23
    ä¸Ģæĸ¹éĿ¢
    -0.23
    POSITIVE LOGITS
     Reviewed
    0.27
     Bast
    0.25
     bast
    0.25
    resultado
    0.24
    _po
    0.24
    FAIL
    0.24
     Po
    0.24
    大家åĪĨ享
    0.24
    _hpp
    0.24
    refix
    0.23
    Activations Density 1.017%

    No Known Activations

    This feature has no known activations.