© 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. 62608
    Prev
    Next
    INDEX
    Explanations

    percentage increase or decrease

    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
    éĢĨ
    -0.08
    æĿİåŃIJ
    -0.07
    æ¦Ĥ
    -0.06
     Central
    -0.06
    æ¡ĥæĿİ
    -0.06
    åįĪ
    -0.06
    æ¬ł
    -0.06
    hof
    -0.06
    ^{-
    -0.06
     Reverse
    -0.06
    POSITIVE LOGITS
    atched
    0.09
    æĮīæ¯Ķä¾ĭ
    0.08
    ÐĴÐIJ
    0.08
    ))->
    0.07
    éĵ¶å±±
    0.07
    红æĸij
    0.07
    æłª
    0.07
    rael
    0.07
    agal
    0.07
    rego
    0.07
    Activations Density 0.087%

    No Known Activations