© 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. 31530
    Prev
    Next
    INDEX
    Explanations

    test, however, however

    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
    æ½ĩæ¹ĺ
    -0.07
    sker
    -0.07
    ÑĦеÑĢ
    -0.07
    uth
    -0.07
    ÅŁk
    -0.07
    bey
    -0.07
    ussin
    -0.07
     concerti
    -0.07
    abee
    -0.07
    itage
    -0.07
    POSITIVE LOGITS
    çļĦçĶµåŃIJ
    0.07
    åĵī
    0.06
     electronic
    0.06
    ÙĦÙĪ
    0.06
     elettr
    0.06
    ä¸İä¼Ĺ
    0.06
     electron
    0.06
    lec
    0.06
    æ¯ģ
    0.06
    ÑıÑĤ
    0.06
    Activations Density 0.594%

    No Known Activations