© 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. 28771
    Prev
    Next
    INDEX
    Explanations

    no

    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
     somewhat
    -0.09
    èĢĮä¸įæĺ¯
    -0.09
    æľīä¸Ģå®ļ
    -0.08
     sometime
    -0.08
    èĢĮéĿŀ
    -0.08
     various
    -0.08
     several
    -0.08
    åħ·æľīä¸Ģå®ļ
    -0.08
    æľīä¸ĢäºĽ
    -0.08
    æľīä¸Ģå®ļçļĦ
    -0.08
    POSITIVE LOGITS
    åı¯è¨Ģ
    0.19
     whatsoever
    0.18
     anymore
    0.14
     سÙĪÙī
    0.13
    æĪĸå°ij
    0.12
     žádn
    0.11
    ä»»ä½ķ人
    0.11
    æıIJä¾Ľä»»ä½ķ
    0.11
    ä¹Łæ²¡æľī
    0.11
    åģļä»»ä½ķ
    0.11
    Activations Density 0.145%

    No Known Activations