© 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. 29458
    Prev
    Next
    INDEX
    Explanations

    Abbreviations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ricula
    -0.26
    quin
    -0.26
    è¾Ī
    -0.25
    ç»´
    -0.25
    Ñģки
    -0.25
    erez
    -0.25
    petition
    -0.25
    å¥
    -0.24
    quina
    -0.24
    对ç«ĭ
    -0.24
    POSITIVE LOGITS
    æ´ŀ
    0.28
    express
    0.28
    GENERAL
    0.27
    -general
    0.27
    ADV
    0.26
    DE
    0.25
    athe
    0.25
    æ³ĵ
    0.25
    general
    0.24
    åĴ¨è¯¢æľįåĬ¡
    0.24
    Activations Density 1.360%

    No Known Activations