© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 776
    Prev
    Next
    INDEX
    Explanations

    steam generator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    åı¸æ³ķæīĢ
    -0.08
    Git
    -0.07
    perse
    -0.07
    æ¯ıæĿ¡
    -0.07
    zak
    -0.07
     Scaffold
    -0.07
    oucher
    -0.06
    пÑĭ
    -0.06
    ishi
    -0.06
    çł¥
    -0.06
    POSITIVE LOGITS
     steam
    0.13
    èĴ¸æ±½
    0.11
     Steam
    0.10
     boilers
    0.09
    Steam
    0.09
     vapeur
    0.09
    steam
    0.09
     boiler
    0.09
    èĴ¸æ°Ķ
    0.09
    éĶħçĤī
    0.09
    Activations Density 0.012%

    No Known Activations