© 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. 33-TRANSCODER-HP
    7. 54686
    Prev
    Next
    INDEX
    Explanations

    language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     mouths
    -0.30
    çĶŁäº§èĥ½åĬĽ
    -0.28
    è§ĦåĪĴ建设
    -0.28
    å·¥ç¨ĭæĸ½å·¥
    -0.26
     ìĥĿìĤ°
    -0.26
    çĶŁçĶ¢
    -0.25
     capabilities
    -0.25
    æŃ¥
    -0.25
    /resources
    -0.24
    languages
    -0.24
    POSITIVE LOGITS
    stock
    0.32
     stock
    0.31
     Stock
    0.28
    Stock
    0.28
    rium
    0.27
    举æĸ¹
    0.26
    itur
    0.25
    å°±è§īå¾Ĺ
    0.25
    äºĨä¸ĢäºĽ
    0.24
    (stock
    0.24
    Activations Density 0.011%

    No Known Activations