© 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. 18-TRANSCODER-HP
    7. 90328
    Prev
    Next
    INDEX
    Explanations

    Book/movie reviews and summaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    omnia
    -0.29
    æ²»çĸĹæĸ¹æ³ķ
    -0.28
    struk
    -0.27
     connections
    -0.26
     NOI
    -0.25
    è¿ĻæĿ¡
    -0.25
    åŁºæľ¬ä¿¡æģ¯
    -0.25
    riz
    -0.24
    alus
    -0.24
     probs
    -0.24
    POSITIVE LOGITS
    åĴĴ
    0.26
    ä¸Ģå¤ľ
    0.26
    .Minute
    0.25
    Ủ
    0.25
    æĪijè¿ĺ
    0.24
    urnal
    0.24
     footnote
    0.24
    itat
    0.24
    æľŃ
    0.24
     phiếu
    0.23
    Activations Density 26.770%

    No Known Activations