© 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. 45510
    Prev
    Next
    INDEX
    Explanations

    functioning correctly and as expected

    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
    åѦèĢĮ
    -0.07
    æѦ
    -0.07
    —which
    -0.06
    ç´¢æĢ§
    -0.06
     dess
    -0.06
     HAR
    -0.06
    _OPT
    -0.06
    utton
    -0.06
    éĤ£åı¯
    -0.06
    æĢ§æĪĸ
    -0.06
    POSITIVE LOGITS
    çļĦåIJĹ
    0.11
    åĹİ
    0.10
    åIJĹ
    0.10
    äºĨåIJĹ
    0.10
    没æľīéĹ®é¢ĺ
    0.08
    äºĨåĹİ
    0.08
    ump
    0.08
    è¦ģ注æĦıçļĦæĺ¯
    0.07
    ä¸įèµ·æĿ¥
    0.07
    åĽłä¸ºåľ¨
    0.07
    Activations Density 0.024%

    No Known Activations