© 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. 128907
    Prev
    Next
    INDEX
    Explanations

    Sharing information

    np_max-act · gemini-2.0-flash
    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
    agate
    -0.27
    imir
    -0.27
    compute
    -0.25
    acus
    -0.25
    omer
    -0.25
    äºı
    -0.24
    ique
    -0.24
     Voters
    -0.24
    æ³³
    -0.24
    await
    -0.24
    POSITIVE LOGITS
    鬣
    0.30
    æ¿Ģ
    0.30
    _RCC
    0.28
    æĹ¥æ¶Īæģ¯
    0.27
     drift
    0.26
    æİĩ
    0.26
    ản
    0.25
    åĴ¥
    0.25
    _VOL
    0.24
     Legacy
    0.24
    Activations Density 0.006%

    No Known Activations