© 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. 129089
    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
    alternate
    -0.32
    cccc
    -0.27
     kh
    -0.26
     nowrap
    -0.25
    äº¤æĽ¿
    -0.24
    èĬĤ课
    -0.23
    åijĬè¯ī她
    -0.23
     comprising
    -0.23
    便åı¯
    -0.23
     alternating
    -0.23
    POSITIVE LOGITS
    gger
    0.29
    èĴĻ
    0.29
    asers
    0.26
    YLON
    0.26
    æĪij们éĥ½
    0.25
     ours
    0.24
    ViewState
    0.24
    èļ¤
    0.24
    rai
    0.23
    Mont
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.