© 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. 57556
    Prev
    Next
    INDEX
    Explanations

    dysfunctions, diseases, nurses, wavelengths, printing

    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
    —or
    -0.07
    ãģĹãģĭãĤĤ
    -0.06
    ç»Ŀ
    -0.06
    æ¡¿
    -0.06
    —
    -0.06
    æľĢåħ³éĶ®
    -0.06
    alice
    -0.06
    —and
    -0.06
    è¿ĻæŃ£æĺ¯
    -0.06
    åį´
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.13
    诸å¦Ĥ
    0.12
     ebenfalls
    0.11
    çļĦè¿ĺæľī
    0.10
     nữa
    0.10
     miscellaneous
    0.10
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.10
    ãģªãģ©ãĤĤ
    0.10
    çļĦåħ¶ä»ĸ
    0.09
    ÙģÙĪ
    0.09
    Activations Density 0.041%

    No Known Activations