© 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. 30249
    Prev
    Next
    INDEX
    Explanations

    computers and operating systems

    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
     demographic
    -0.28
    icals
    -0.25
     DEFINE
    -0.24
    ++];↵
    -0.24
    ogue
    -0.23
    æ´»è·ĥ
    -0.23
    åijĬè¯ī大家
    -0.23
    .diff
    -0.23
     Raider
    -0.23
    endphp
    -0.23
    POSITIVE LOGITS
    åIJĮèĥŀ
    0.29
    为ä¸ŃåĽ½
    0.25
    æī£
    0.25
    çŃ·åŃIJ
    0.24
    post
    0.24
    对ä¸ŃåĽ½
    0.24
     Eastern
    0.24
    طر
    0.24
    èĢ³
    0.24
    襻
    0.23
    Activations Density 0.941%

    No Known Activations