© 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. 31472
    Prev
    Next
    INDEX
    Explanations

    typescript generics extend

    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
    vic
    -0.07
    éĺ¿æĭī伯
    -0.06
    .makedirs
    -0.06
     EITHER
    -0.06
    ικο
    -0.06
    è§Ĵ度æĿ¥çľĭ
    -0.06
    æ°¨éħ¸
    -0.06
     inilah
    -0.06
    åģ¥åº·ç½ij
    -0.06
    åijĬè¯ī大家
    -0.06
    POSITIVE LOGITS
    æĪijåIJĹ
    0.09
    åĹİ
    0.08
    å¹´å¢ŀéķ¿
    0.08
    çļĭ
    0.07
    èĭ¥æľī
    0.07
    åIJĹ
    0.07
    æŶæīį
    0.07
    odat
    0.07
    羣æľī
    0.07
    èĭ¥æĺ¯
    0.07
    Activations Density 0.041%

    No Known Activations