© 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. 64537
    Prev
    Next
    INDEX
    Explanations

    unit conversions

    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
    èĩªè§īéģµå®Ī
    -0.07
    rano
    -0.07
    onom
    -0.07
    å®īéĿĻ
    -0.07
    åIJijä¸ĭ
    -0.07
    ä¸İæĻ®éĢļ
    -0.07
    aft
    -0.07
     اÙĦجÙĩ
    -0.06
    .sec
    -0.06
    ä¸įèµ·çľ¼
    -0.06
    POSITIVE LOGITS
     equivalents
    0.10
    æį¢ç®Ĺ
    0.10
     translations
    0.09
     translation
    0.09
     equivalent
    0.09
     translator
    0.09
    转æį¢
    0.09
    éĤ£è¾¹çļĦ
    0.09
    ç¿»è¯ij
    0.09
    è¯ij
    0.08
    Activations Density 0.007%

    No Known Activations