© 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. 24428
    Prev
    Next
    INDEX
    Explanations

    names of authors and artists

    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
    å§Ĺ
    -0.08
    wel
    -0.07
    çĺª
    -0.07
    çļĦä¸Ģå®ļ
    -0.07
    سÙĪÙĨ
    -0.07
     [["
    -0.07
     folly
    -0.07
    æ½°
    -0.07
    èĹ
    -0.07
    å°±æĺ¯ä½łçļĦ
    -0.06
    POSITIVE LOGITS
    trag
    0.07
    æĨij
    0.07
    ghi
    0.07
    ä¸įä»ħåľ¨
    0.06
    alsy
    0.06
    usse
    0.06
    ussin
    0.06
    å¤ļ好
    0.06
    aldas
    0.06
    azī
    0.06
    Activations Density 0.087%

    No Known Activations