© 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. 60028
    Prev
    Next
    INDEX
    Explanations

    lead ore

    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
    stral
    -0.07
    ä¸įçŁ¥éģĵä½ł
    -0.07
    aeda
    -0.07
    .creation
    -0.07
    egur
    -0.07
    CUS
    -0.06
    ç¼ĸè¾ijæݨèįIJ
    -0.06
    xCE
    -0.06
    иÑħ
    -0.06
    ÙĤات
    -0.06
    POSITIVE LOGITS
    è¡Įä¹ĭ
    0.07
    |int
    0.07
    ÅĤaszc
    0.07
    è¡ĮçļĦ
    0.07
     Sie
    0.07
    جÙĪ
    0.07
    为ä»Ģä¹Ī
    0.07
    achim
    0.07
    è¿Ļ份
    0.07
    ï½ľ
    0.07
    Activations Density 0.095%

    No Known Activations