© 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. 48059
    Prev
    Next
    INDEX
    Explanations

    noun phrases or categories

    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
    arka
    -0.06
    ä¸ĬçīĮ
    -0.06
    Úĺ
    -0.05
    à¹Į
    -0.05
    宵
    -0.05
    ÙĩÙĬر
    -0.05
    åĩĨåĪĻ
    -0.05
    ç¾İæľ¯åѦéĻ¢
    -0.05
    ãĢIJ
    -0.05
    Decode
    -0.05
    POSITIVE LOGITS
     jewe
    0.08
    ä¸Ńåħ·æľī
    0.08
    为å®ŀçİ°
    0.08
    menta
    0.08
    è¿ŀæİ¥æľī
    0.08
    建设åĴĮ
    0.08
    ç§įç±»ç¹ģå¤ļ
    0.08
     Leverkus
    0.08
    çļĦåĨħ涵
    0.08
    æĺ¯äººä»¬
    0.08
    Activations Density 0.016%

    No Known Activations