© 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. 51317
    Prev
    Next
    INDEX
    Explanations

    optical lens and panel

    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
    ä¸Ģå¦Ĥ
    -0.08
    accio
    -0.08
    icing
    -0.08
    ä½ĥ
    -0.07
    ichten
    -0.07
    ocket
    -0.07
    庸
    -0.07
    italic
    -0.07
    æĭĹ
    -0.07
    å¦Ĥåħ¶
    -0.07
    POSITIVE LOGITS
    è¿ĶåĽŀåĪĹ表
    0.07
     sỹ
    0.07
     Frat
    0.07
    该éķĩ
    0.07
    å°ıæĸ°
    0.07
    deka
    0.06
    eu
    0.06
    _LIBRARY
    0.06
    绥
    0.06
    å½Ĵç±»
    0.06
    Activations Density 0.015%

    No Known Activations