© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62122
    Prev
    Next
    INDEX
    Explanations

    article or tips below

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åĩ¡æľ¬ç½ij注æĺİ
    -0.10
    iver
    -0.08
    é¼ĵåĬ±åѦçĶŁ
    -0.08
    ucci
    -0.08
    omez
    -0.08
     mies
    -0.08
    å¾·æĸ¯
    -0.08
    åħ¬åı¸èį£èªī
    -0.08
    æĸ°ä¹¦æݨèįIJ
    -0.07
    ä¸Ģå®ļè¦ģæľī
    -0.07
    POSITIVE LOGITS
    æĪij们就æĿ¥
    0.08
     below
    0.07
    å°±çĶ±
    0.07
    就让
    0.07
     ниже
    0.07
    ä¸Ģèµ·åİ»
    0.06
     share
    0.06
    æľ¬æĸĩå°Ĩ
    0.06
    å°±æĿ¥
    0.06
     shall
    0.06
    Activations Density 0.866%

    No Known Activations