© 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. 26697
    Prev
    Next
    INDEX
    Explanations

    canonical and noncanonical

    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
    ä¸Ģæł·çļĦ
    -0.07
    æĪijæĿ¥
    -0.07
    ä¸Ģä½ĵ
    -0.07
     táºŃt
    -0.06
    пеÑĤ
    -0.06
    missions
    -0.06
    ä¸Ģä½ĵçļĦ
    -0.06
    ëij¥
    -0.06
    miss
    -0.06
    解éĩĬéģĵ
    -0.06
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.19
    /non
    0.18
    æĪĸä¸į
    0.17
    ä¸İéĿŀ
    0.17
    åĴĮéĿŀ
    0.16
    æĪĸéĿŀ
    0.16
    åĴĮä¸į
    0.14
    less
    0.12
    åIJ¦
    0.12
     ÙĪغÙĬر
    0.12
    Activations Density 0.411%

    No Known Activations