© 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. 21355
    Prev
    Next
    INDEX
    Explanations

    version number or sales

    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
     Emp
    -0.08
    emp
    -0.07
    举个ä¾ĭåŃIJ
    -0.07
    èĸªèµĦå¾ħéģĩ
    -0.07
    Emp
    -0.07
    ä¾ĭå¦Ĥ
    -0.07
     mouseX
    -0.06
    çļĦæķ°æį®æĺ¾ç¤º
    -0.06
    åħ·ä½ĵæĿ¥è¯´
    -0.06
    aliste
    -0.06
    POSITIVE LOGITS
     desac
    0.07
    室å¤ĸ
    0.07
    crawler
    0.07
     ÑĩиÑģÑĤо
    0.07
    пÑĢоÑĩем
    0.07
    ä¹ĭä¸į
    0.06
    ç«ĭä¸ļ
    0.06
    atto
    0.06
    _context
    0.06
     methodology
    0.06
    Activations Density 0.072%

    No Known Activations