© 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. 56644
    Prev
    Next
    INDEX
    Explanations

    non-trivial examples

    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
    寡
    -0.08
    ÓĻÑĢ
    -0.07
    ÙĪات
    -0.07
    IFO
    -0.07
    éĿ¢æĹł
    -0.07
    hart
    -0.07
     retro
    -0.07
    对åı£
    -0.06
    æĪĸèĢħæĺ¯
    -0.06
    é»Ħé¾Ļ
    -0.06
    POSITIVE LOGITS
    æĹ¢ä¸į
    0.09
     ненÑĥ
    0.09
    æĹ¢
    0.09
    åĮºåĪ«äºİ
    0.09
     distinct
    0.09
    ä»ĭäºİ
    0.09
     neither
    0.08
    æľīæĦıä¹ī
    0.08
    åıĪä¸įæĺ¯
    0.08
    ä¸įçĦ¶
    0.08
    Activations Density 0.077%

    No Known Activations