© 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. 11699
    Prev
    Next
    INDEX
    Explanations

    scientific notation numbers

    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
    å®ħ
    -0.08
    å¤ľæ·±
    -0.08
    åĵī
    -0.08
    del
    -0.07
     ока
    -0.07
    istribute
    -0.07
    elay
    -0.07
    =time
    -0.07
    åij±
    -0.07
    çŃł
    -0.07
    POSITIVE LOGITS
    usic
    0.06
    اÛĮØ´
    0.06
    æĻ¶æĻ¶
    0.06
    好åĥıæĺ¯
    0.06
    æīĵæĿ¥
    0.06
     null
    0.06
    å±ħçĦ¶æĺ¯
    0.06
    itim
    0.06
     Weiner
    0.06
    ×ľ×ª
    0.06
    Activations Density 0.010%

    No Known Activations