© 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. 65310
    Prev
    Next
    INDEX
    Explanations

    trim removes whitespace

    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
    apis
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.07
    ç«Ł
    -0.07
    婧
    -0.07
    æīĢ欲
    -0.06
    /tiny
    -0.06
    éļĶ
    -0.06
    åIJįåī¯åħ¶å®ŀçļĦ
    -0.06
    çĶ¸
    -0.06
    è¯
    -0.06
    POSITIVE LOGITS
     unrelated
    0.08
    主è¦ģçĶ¨äºİ
    0.08
     ì£¼ë¡ľ
    0.07
     Won
    0.07
     various
    0.07
    侧éĩįäºİ
    0.07
    ocused
    0.07
     eher
    0.07
    主è¦ģç»ıèIJ¥
    0.07
    æ¶īåıĬ
    0.07
    Activations Density 0.017%

    No Known Activations