© 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. 11589
    Prev
    Next
    INDEX
    Explanations

    elegant way or solution

    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®ŀå®ŀåľ¨åľ¨çļĦ
    -0.08
    æ¦Ķ
    -0.08
    à¸łà¸²à¸Ħ
    -0.08
    峪
    -0.08
    æ²īæ²ī
    -0.07
    oids
    -0.07
    liable
    -0.07
    å®ŀå®ŀåľ¨åľ¨
    -0.07
    ptions
    -0.07
    èĥ½èĢIJ
    -0.07
    POSITIVE LOGITS
    ä¹ĭå¤Ħåľ¨äºİ
    0.08
     léo
    0.08
    (er
    0.08
    antly
    0.08
    æİĴçīĪ
    0.07
     yet
    0.07
     eleg
    0.07
    çĦ¶
    0.07
    jero
    0.07
     simplicity
    0.07
    Activations Density 0.010%

    No Known Activations