© 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. 34281
    Prev
    Next
    INDEX
    Explanations

    . or :

    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
    æŁIJç§įç¨ĭ度ä¸Ĭ
    -0.07
    ä¼¼ä¹İä¹Ł
    -0.07
    æŁIJç§įæĦıä¹īä¸Ĭ
    -0.07
    _BG
    -0.06
    erva
    -0.06
     leid
    -0.06
    angkat
    -0.06
    家ä¼Ļ
    -0.06
    acom
    -0.06
    æıIJä¾ĽäºĨä¸Ģ个
    -0.06
    POSITIVE LOGITS
    æīĵæ¶Ī
    0.08
    åĬ¨åĬ¨
    0.07
    aleb
    0.07
    busters
    0.07
    NEY
    0.07
    .alt
    0.07
    ritt
    0.07
    aires
    0.07
    ecem
    0.07
    acked
    0.06
    Activations Density 0.011%

    No Known Activations