© 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. 27-TRANSCODER-HP
    7. 58498
    Prev
    Next
    INDEX
    Explanations

    Code, URLs, comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¥ĹæĪ¿
    -0.28
    viso
    -0.25
     fixation
    -0.25
    çļĦå°±æĺ¯
    -0.24
     ann
    -0.24
    åįķåħĥ
    -0.24
    alloca
    -0.24
    ãģ®ãĤĤ
    -0.24
     verdiÄŁi
    -0.23
    èģĶ
    -0.23
    POSITIVE LOGITS
     sometimes
    0.43
     eventually
    0.42
    æľīæŶåĢĻ
    0.40
    æľīæŶ
    0.38
     today
    0.36
     otherwise
    0.36
     somehow
    0.35
     someday
    0.35
     traditionally
    0.34
    ä»Ĭ天
    0.33
    Activations Density 0.002%

    No Known Activations