© 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. 113067
    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
    =out
    -0.28
     out
    -0.26
    èµ°åĩºæĿ¥
    -0.25
    说æĺ¯
    -0.25
     crystall
    -0.24
    é¾Ī
    -0.24
    closing
    -0.24
    æľºèĥ½
    -0.24
    cut
    -0.24
    ç»Ĩèħ»
    -0.24
    POSITIVE LOGITS
    wick
    0.27
     phú
    0.26
    ieres
    0.26
    IPH
    0.25
    ffa
    0.25
    xEA
    0.25
    abee
    0.25
    éĶ¦æłĩ
    0.25
    ToF
    0.24
    erais
    0.24
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.