© 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. 15850
    Prev
    Next
    INDEX
    Explanations

    numbers after digits

    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
    ·
    -0.07
    ¹
    -0.07
    ä¹ĭ家
    -0.06
    anggap
    -0.06
    ä¹ĭ士
    -0.06
    ´
    -0.06
    strup
    -0.06
    weise
    -0.06
    ä¸Ģå¸Ĩ
    -0.06
    ujuk
    -0.06
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.09
    ãģĿãĤĮãĤĤ
    0.08
    æĪijè¦ģè¯Ħ论
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    omething
    0.08
    æ¯ĽéĴ±
    0.08
    ä¸Ģå¹´ä¸Ģ度çļĦ
    0.08
     Aé
    0.08
    ourcem
    0.07
    omis
    0.07
    Activations Density 0.019%

    No Known Activations