© 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. 97074
    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
    ä¸Ģç±»
    -0.29
    unger
    -0.27
    æ´ŀ
    -0.26
    ä¸Ģ群
    -0.25
     void
    -0.25
    %@
    -0.25
    /article
    -0.25
    (mut
    -0.24
    unal
    -0.24
    umping
    -0.24
    POSITIVE LOGITS
    æłĪ
    0.32
    èĥ½å¾ĹåĪ°
    0.28
    庶
    0.27
    idente
    0.26
    phabet
    0.25
    anja
    0.25
    æĴ¼
    0.25
     Credits
    0.25
     Prob
    0.25
     probably
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.