© 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. 13008
    Prev
    Next
    INDEX
    Explanations

    code snippets or non-English phrases

    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
    lete
    -0.07
    ستÙĬ
    -0.07
    lade
    -0.07
    ÙĦÙĪب
    -0.07
    ä¸Ĭåı£
    -0.07
    biz
    -0.06
    pees
    -0.06
    akter
    -0.06
    imens
    -0.06
    ithub
    -0.06
    POSITIVE LOGITS
    æł¹æį®ä½łçļĦ
    0.07
    ×ļ
    0.07
    é¾Ļæ¹¾
    0.07
    åŃ¦æł¡
    0.07
    ione
    0.06
    ä¿Ŀåį«æĪĺ
    0.06
    anine
    0.06
     spar
    0.06
    æĿŀ
    0.06
    μί
    0.06
    Activations Density 0.001%

    No Known Activations