© 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. 99098
    Prev
    Next
    INDEX
    Explanations

    %

    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
    otti
    -0.29
    ä¸Ģèµ·æĿ¥
    -0.28
    _aff
    -0.28
     equally
    -0.26
    root
    -0.25
     dispose
    -0.25
    Republic
    -0.24
    æł¹
    -0.24
     ul
    -0.24
    zá
    -0.24
    POSITIVE LOGITS
    sic
    0.28
    å¹²åĺĽ
    0.27
    obo
    0.26
    çļĦæĸ¹å¼ı
    0.25
     PackageManager
    0.24
    criptive
    0.24
    æĻºæħ§åŁİå¸Ĥ
    0.24
    ivas
    0.23
    èĶĹ
    0.23
    ë¹Ħìļ©
    0.23
    Activations Density 0.022%

    No Known Activations