© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60100
    Prev
    Next
    INDEX
    Explanations

    ISO certification and accreditation

    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
    olini
    -0.08
    å®ŀéªĮä¸Ń
    -0.08
    æĥħåĨµè¯´æĺİ
    -0.07
    дли
    -0.07
    严åİīæīĵåĩ»
    -0.07
    Aliases
    -0.07
    èѦæĥķ
    -0.07
    ,proto
    -0.07
     restri
    -0.07
    é¢ĦåĪ¤
    -0.07
    POSITIVE LOGITS
     ISO
    0.10
    ISO
    0.09
    åĽ½éĻħæłĩåĩĨ
    0.08
    /framework
    0.08
    .documentElement
    0.08
    èĩªè¯Ħ
    0.08
    èĩªæĪijè¯Ħä»·
    0.07
    æĿ¡çIJĨ
    0.07
    (Process
    0.07
     organis
    0.07
    Activations Density 0.056%

    No Known Activations