© 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. 131039
    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
    _dw
    -0.27
    [number
    -0.25
     Trials
    -0.25
    æķ´ä¸ªäºº
    -0.25
     veins
    -0.25
    EFR
    -0.24
    ingen
    -0.24
     ventures
    -0.24
    éĻĤ
    -0.24
    .ser
    -0.24
    POSITIVE LOGITS
    æĿ¥æī¾
    0.31
    åħij
    0.29
    éĢĨ
    0.28
    æĿ¥åģļ
    0.27
    le
    0.24
    izi
    0.24
    è¿Ľåĩº
    0.24
    第
    0.24
    åıĮåIJij
    0.24
    éĺį
    0.23
    Activations Density 0.004%

    No Known Activations