© 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. 51601
    Prev
    Next
    INDEX
    Explanations

    discharge, bile, content

    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
    åħ¨å±Ģ
    -0.07
    inari
    -0.07
    ç«ĭåľ¨
    -0.07
     permanently
    -0.07
    æ°¸æģĴ
    -0.06
    izoph
    -0.06
    uni
    -0.06
    æ°¸ä¹ħ
    -0.06
     Folha
    -0.06
    inaire
    -0.06
    POSITIVE LOGITS
    æİĴåĩº
    0.10
    è´¨åľ°
    0.09
    éĩıå°ij
    0.09
    è´¨
    0.09
    åIJ«æľī丰å¯ĮçļĦ
    0.09
    åĪĨæ³Įçī©
    0.09
    æİĴæ³Ħ
    0.09
     конÑģиÑģÑĤен
    0.09
    ç²ĺ稳
    0.09
    åIJ«æľī
    0.09
    Activations Density 0.042%

    No Known Activations