© 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. 49492
    Prev
    Next
    INDEX
    Explanations

    chemical and scientific investigations

    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
    æł·åŃIJ
    -0.10
    å¾Īå¤ļåľ°æĸ¹
    -0.08
    åĴĮæľīåħ³
    -0.08
    สมุà¸Ĺร
    -0.08
    Statistic
    -0.07
    æĶ¾ä¸Ĭ
    -0.07
    çīĪæĿĥçŃī
    -0.07
    樣
    -0.07
    æĢ»ä½ĵæĿ¥è¯´
    -0.07
    æĺ¯ä¸ĢèĪ¬
    -0.07
    POSITIVE LOGITS
    eed
    0.08
    zyn
    0.07
    éĺģä¸ĭ
    0.07
    èĬ¥
    0.07
    缨
    0.06
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.06
    æĹłä»»ä½ķ
    0.06
    thed
    0.06
    æŁIJ
    0.06
     herein
    0.06
    Activations Density 0.020%

    No Known Activations