© 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. 28314
    Prev
    Next
    INDEX
    Explanations

    line, row, page, sheet, domain, series

    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
    æ°´æĺ¯
    -0.07
    åħīæĺ¯
    -0.06
    è¾ĥåݻ年åIJĮæľŁ
    -0.06
     cardinal
    -0.06
    stav
    -0.06
    |%
    -0.06
    åIJijæ³ķéĻ¢
    -0.06
    çĻ¾èī²
    -0.06
    %S
    -0.06
    Ø·ÙĦ
    -0.06
    POSITIVE LOGITS
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.09
    æĪIJ羣
    0.09
    heen
    0.08
    '][$
    0.08
    atrix
    0.08
    ç«ĭ交
    0.08
    éĢ¼äºº
    0.07
    ][]
    0.07
    ingin
    0.07
    åľºæ¯ĶèµĽä¸Ń
    0.07
    Activations Density 0.041%

    No Known Activations