© 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. 112853
    Prev
    Next
    INDEX
    Explanations

    World

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ£ãģ±
    -0.30
    åĪĴ
    -0.30
    åIJİå¤ĩ
    -0.28
    åĪ®
    -0.27
     Vers
    -0.26
    çļĦçIJĨæĥ³
    -0.26
    纷
    -0.25
    _preference
    -0.24
    sty
    -0.23
    书ä¸Ń
    -0.23
    POSITIVE LOGITS
     &_
    0.25
    æ¯Ľ
    0.25
    管çIJĨ人åijĺ
    0.23
    æĪIJé¾Ļ
    0.23
    åıĪ好
    0.23
    ochen
    0.22
    _Var
    0.22
    urer
    0.22
     spotting
    0.22
     cute
    0.22
    Activations Density 0.006%

    No Known Activations