© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61799
    Prev
    Next
    INDEX
    Explanations

    following

    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
    请åıĤèĢĥ
    -0.07
    ModuleName
    -0.06
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.06
    èĹ
    -0.06
    åı¯çĶ¨çļĦ
    -0.06
     wit
    -0.06
     Middleton
    -0.06
     Olah
    -0.06
    è§Ħ
    -0.06
    æĹłç©·çļĦ
    -0.06
    POSITIVE LOGITS
     seguenti
    0.09
    åħ·æľī以ä¸ĭ
    0.08
     seguente
    0.08
     folgende
    0.08
     ακÏĮ
    0.08
    çİ°åľ¨æĪij们
    0.08
     seguintes
    0.08
     series
    0.07
    ç»ıèIJ¥é¡¹çĽ®
    0.07
    æĪijä¸Ģ个
    0.07
    Activations Density 0.102%

    No Known Activations