© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23083
    Prev
    Next
    INDEX
    Explanations

    and terms

    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
    æĬĢæľ¯çŃī
    -0.07
    人æĪĸ
    -0.07
    åıĬå®īåħ¨
    -0.07
    管çIJĨçŃī
    -0.07
    णà¥Ģ
    -0.07
    пÑĤ
    -0.07
    лика
    -0.07
    åĽ¾çīĩæĪĸ
    -0.07
    åıĬ产åĵģ
    -0.07
    ByUsername
    -0.07
    POSITIVE LOGITS
    ä¸İ
    0.16
     ÙĪبÙĬÙĨ
    0.14
    ãĤĤãģ®ãģ¨
    0.13
     versus
    0.13
     vs
    0.13
    ä¸İçݰ代
    0.13
    ä¸İæīĢè¿°
    0.13
    å®ĥä¸İ
    0.13
    èĪĩ
    0.12
    ä¸İ该
    0.12
    Activations Density 0.171%

    No Known Activations