© 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. 97083
    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
    æĤ¯
    -0.27
    ·
    -0.25
    ãĢĬ
    -0.24
    idades
    -0.23
    never
    -0.23
    yst
    -0.23
    çķĻä¸ĭ
    -0.23
     trails
    -0.23
     Bell
    -0.22
     bur
    -0.22
    POSITIVE LOGITS
    ष
    0.29
    ä¸ĭåİ»
    0.25
    å°ıä¼Ļ伴们
    0.24
    âĢ¦”
    0.23
    WD
    0.23
    rze
    0.23
    åįĴ
    0.23
    íĮħ
    0.23
    upo
    0.23
     Fist
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.