© 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. 49034
    Prev
    Next
    INDEX
    Explanations

    added or fixed

    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
    ÙĪاÙħ
    -0.07
    å¤ļå¹´æĿ¥
    -0.06
    个åŃIJ
    -0.06
    åĵĶ
    -0.06
    è¶Ĭæĥ³
    -0.06
    Cod
    -0.06
    ç»Ń
    -0.06
    æľī人
    -0.06
    ège
    -0.06
    殿ä¸ĭ
    -0.06
    POSITIVE LOGITS
    天å®ī
    0.08
    æĪijåĪļ
    0.08
    adam
    0.08
    èĻŀ
    0.07
    羡
    0.07
    ething
    0.07
    æľ¬é¢ĺåĪĨæŀIJ
    0.07
    å¹´èİ·å¾Ĺ
    0.07
    å¼ķè¿ĽäºĨ
    0.07
    丹丹
    0.07
    Activations Density 0.027%

    No Known Activations