© 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. 20-TRANSCODER-HP
    7. 140573
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ§Į
    -0.30
    {:
    -0.27
    åĿŁ
    -0.26
    å¤ķéĺ³
    -0.26
    ctica
    -0.26
    Ñĩ
    -0.26
    马åĬĽ
    -0.26
    åij¼åºĶ
    -0.26
    ä¸įä¼ļæľī
    -0.25
    åĪĨéĴŁåIJİ
    -0.25
    POSITIVE LOGITS
     broadly
    0.27
    esa
    0.26
    æ·±åİļçļĦ
    0.26
     formally
    0.26
    -sided
    0.26
    袤
    0.26
    odian
    0.25
    -offs
    0.25
    漫éķ¿çļĦ
    0.24
    æ¦ľ
    0.24
    Activations Density 0.299%

    No Known Activations