© 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. 9-TRANSCODER-HP
    7. 29369
    Prev
    Next
    INDEX
    Explanations

    matter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    纸ä¸Ĭ
    -0.29
    æĺ¥ç§ĭ
    -0.27
    pered
    -0.26
    emens
    -0.25
    borough
    -0.25
    ilded
    -0.25
    å¤ĸåĽ½
    -0.25
     thá»Ŀ
    -0.25
    {@
    -0.25
    åħļæĶ¿
    -0.25
    POSITIVE LOGITS
    und
    0.28
    åĿĩ
    0.27
    ell
    0.27
    ocht
    0.27
     Ser
    0.26
    FlowLayout
    0.25
     dos
    0.25
     und
    0.25
     undef
    0.25
    沿
    0.24
    Activations Density 3.557%

    No Known Activations