© 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. 13186
    Prev
    Next
    INDEX
    Explanations

    enterprise applications

    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
    æĺ¾çĦ¶æĺ¯
    -0.08
    设æ³ķ
    -0.07
    شت
    -0.06
    ugg
    -0.06
    feo
    -0.06
    éĤ£ä½łå°±
    -0.06
    ä¸Ĭè¿°äºĭå®ŀ
    -0.06
    éĤ£æĺ¯æĪij
    -0.06
    Ïĥκ
    -0.06
    设
    -0.06
    POSITIVE LOGITS
    leden
    0.08
    irman
    0.07
    ekat
    0.07
    åĩĿç»ĵ
    0.07
    elda
    0.07
    åľ¨æİ¥åıĹ
    0.07
    计è¾ĥ
    0.07
    ÑģмоÑĤÑĢ
    0.07
    çļĦçľ¼çĿĽ
    0.07
    æĸ°çĶŁçļĦ
    0.07
    Activations Density 0.093%

    No Known Activations