© 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. 42891
    Prev
    Next
    INDEX
    Explanations

    community support

    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
    æļ§
    -0.10
    æ¯Ķå¦Ĥåľ¨
    -0.07
     tÅĻeba
    -0.07
    åı¤å±ĭ
    -0.07
    鸳
    -0.07
    éģ¨
    -0.07
    ä¸Ģ缮
    -0.07
    pper
    -0.07
    åı£æīį
    -0.07
    oi
    -0.07
    POSITIVE LOGITS
    åħ¼åħ·
    0.09
    æĹ¢åı¯
    0.08
    ç³»ç»Łå·¥ç¨ĭ
    0.07
    人ä¸İèĩªçĦ¶
    0.07
    æĹ¢èĥ½
    0.07
    gard
    0.07
     ecosystem
    0.07
    åħ·
    0.07
    uzz
    0.07
    anvas
    0.07
    Activations Density 0.027%

    No Known Activations