© 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. 51055
    Prev
    Next
    INDEX
    Explanations

    more money

    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
    åIJİåį³
    -0.08
    åĿĩæĿ¥èĩª
    -0.08
    æ¸ĭ
    -0.08
    avage
    -0.08
    ä¸Ģä¸ĭå°±
    -0.08
    è¿ĺæĺ¯æľīäºĽ
    -0.08
    kev
    -0.08
    udur
    -0.08
    åħ®
    -0.08
    UTH
    -0.08
    POSITIVE LOGITS
     vice
    0.08
    缸åºĶçļĦ
    0.08
     convers
    0.07
    åıįè¿ĩæĿ¥
    0.07
    å°±ä¼ļæľī
    0.07
    翻天
    0.06
    åıįä¹ĭ
    0.06
    æ¦ľ
    0.06
    åijĹ
    0.06
     Punch
    0.06
    Activations Density 0.015%

    No Known Activations