© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88494
    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
    xon
    -0.28
    çļĦè®°å¿Ĩ
    -0.27
     suffer
    -0.26
    带æĿ¥
    -0.26
     sob
    -0.25
    nist
    -0.24
    帶ä¾Ĩ
    -0.24
    æĸ¼æĺ¯
    -0.24
    unter
    -0.24
    ä¸Ģ个éĹ®é¢ĺ
    -0.24
    POSITIVE LOGITS
    è¯ģ
    0.28
    EP
    0.27
     prelim
    0.25
    ä¸įä»ħä»ħæĺ¯
    0.25
    zellik
    0.25
    chy
    0.24
     initialState
    0.24
    ayout
    0.24
    YYY
    0.23
    alars
    0.23
    Activations Density 2.308%

    No Known Activations

    This feature has no known activations.