© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14109
    Prev
    Next
    INDEX
    Explanations

    separation technique

    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
    hamster
    -0.09
    è´¨éĩı为
    -0.08
    accio
    -0.08
    kini
    -0.08
    ardi
    -0.08
    åħŃåIJĪ
    -0.08
     Padang
    -0.08
    icot
    -0.07
    istrator
    -0.07
    arend
    -0.07
    POSITIVE LOGITS
    æĺ¯æł¹æį®
    0.10
    æĺ¯åŁºäºİ
    0.09
     unequal
    0.09
    ä¸įåĿĩ
    0.09
    åŁºäºİ
    0.09
     differential
    0.09
    æ·±æµħ
    0.09
     based
    0.09
    é«ĺä½İ
    0.09
    对ä¸įåIJĮ
    0.08
    Activations Density 0.063%

    No Known Activations