© 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. 56517
    Prev
    Next
    INDEX
    Explanations

    academic study context

    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
    iment
    -0.06
    ling
    -0.06
    cher
    -0.06
    ymes
    -0.06
    igr
    -0.06
    asseur
    -0.06
     fork
    -0.06
     ((*
    -0.06
    æĦıæĢĿæĺ¯
    -0.06
    ensif
    -0.06
    POSITIVE LOGITS
    为äºĨç»Ļ
    0.09
    åĢ¼å¾Ĺä¸ĢæıIJçļĦæĺ¯
    0.09
    ä¼ĹæīĢåij¨çŁ¥
    0.08
     közül
    0.08
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.08
    baka
    0.08
    究竣æĺ¯ä»Ģä¹Ī
    0.07
    尽管å¦ĤæѤ
    0.07
    isione
    0.07
    åĢ¼å¾Ĺ注æĦıçļĦæĺ¯
    0.07
    Activations Density 0.324%

    No Known Activations