© 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. 30-TRANSCODER-HP
    7. 97086
    Prev
    Next
    INDEX
    Explanations

    architecture

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    licer
    -0.31
    xit
    -0.28
    èĭ¦
    -0.28
    对æİ¥
    -0.28
     trần
    -0.27
    å®īæİĴ
    -0.27
    æİ¥éĢģ
    -0.26
     setContent
    -0.25
    nect
    -0.25
    prises
    -0.25
    POSITIVE LOGITS
     styles
    0.34
     style
    0.33
    æł·å¼ı
    0.30
    style
    0.29
    /engine
    0.28
    IME
    0.27
    çıįçıł
    0.27
     vern
    0.27
    é£İæł¼
    0.26
    å¸ĥ
    0.26
    Activations Density 0.018%

    No Known Activations