© 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. 43955
    Prev
    Next
    INDEX
    Explanations

    answer is

    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
    èĢĮä¸Ķè¿ĺæĺ¯
    -0.09
    дови
    -0.08
    oord
    -0.08
    بÙĥ
    -0.07
    人åħ³æ³¨
    -0.07
     ziem
    -0.07
    _COMPLETE
    -0.07
    ä½ľåĪĻ
    -0.07
    imest
    -0.07
    åįłæĢ»
    -0.07
    POSITIVE LOGITS
    annya
    0.08
    ¨
    0.07
    è¹
    0.07
    ä¸İåIJ¦
    0.07
    åľ¨äºİ
    0.07
    à¸Ńยูà¹Īà¸Ĺีà¹Ī
    0.07
     is
    0.06
    ayaan
    0.06
    ä¹ĭä¸Ģæĺ¯
    0.06
     Ellen
    0.06
    Activations Density 0.008%

    No Known Activations