© 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. 131237
    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
    ewis
    -0.27
    Mex
    -0.26
    yers
    -0.26
    èģļä¼ļ
    -0.25
     kontakt
    -0.25
     Braz
    -0.25
     Mexican
    -0.25
     DRIVER
    -0.25
     Tucson
    -0.25
    èģļ
    -0.25
    POSITIVE LOGITS
    æĬķèŀįèµĦ
    0.29
    INC
    0.28
    åĨ¼
    0.27
    zeich
    0.26
    posit
    0.25
    inary
    0.24
    -inc
    0.24
    ä¸ĭåįĬ
    0.24
    é«ĺä¸ī
    0.24
    vard
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.