© 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. 27-TRANSCODER-HP
    7. 9634
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    poi
    -0.29
    inel
    -0.27
    igel
    -0.27
    iki
    -0.26
    ä½Ļ
    -0.26
     suff
    -0.25
    è´
    -0.25
    æ»ļçIJĥ
    -0.25
    å±ħ
    -0.24
    æĸĩæ¡Ī
    -0.24
    POSITIVE LOGITS
     segreg
    0.27
    å½¢
    0.26
     ãĥĪãĥ©ãĥĥãĤ¯ãĥIJãĥĥãĤ¯
    0.26
    éļľ
    0.26
     lightly
    0.26
    ãĢĬ
    0.26
    stown
    0.25
     strike
    0.25
     favoured
    0.25
    _SS
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.