© 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. 24-TRANSCODER-HP
    7. 151437
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä»»æĢ§
    -0.26
    tek
    -0.26
     Improvement
    -0.25
    -important
    -0.25
    æıª
    -0.24
    anson
    -0.24
    ä»»ä½ķå½¢å¼ı
    -0.24
     wet
    -0.23
    %%%%%%%%
    -0.23
    ä½İåİĭ
    -0.23
    POSITIVE LOGITS
    ector
    0.28
    åĸĭ
    0.25
    ',"
    0.25
    BD
    0.24
    æŁ¥çľĭæĽ´å¤ļ
    0.24
    olia
    0.24
    æĶ»çķ¥
    0.24
     PED
    0.23
    .lang
    0.23
    odia
    0.23
    Activations Density 0.930%

    No Known Activations

    This feature has no known activations.