© 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. 22-TRANSCODER-HP
    7. 111120
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ³ķå®ļ代表
    -0.28
    TA
    -0.26
     TE
    -0.26
     centroid
    -0.26
    å®ī
    -0.26
    磨
    -0.25
    -original
    -0.25
    law
    -0.24
    åı·
    -0.24
     rational
    -0.24
    POSITIVE LOGITS
    acco
    0.28
    .Loader
    0.27
    åĨį说
    0.26
    æŀ¶åŃIJ
    0.26
    è¿Ļ个åIJįåŃĹ
    0.25
     mush
    0.25
    è¢ĭåŃIJ
    0.24
    ACHE
    0.24
    necessary
    0.23
    æĭĸ
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.