© 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. 46458
    Prev
    Next
    INDEX
    Explanations

    Commerce Plaza

    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
    æĮ½çķĻ
    -0.07
    oo
    -0.07
     Shapiro
    -0.06
    ků
    -0.06
    æĺ¯éĿŀ
    -0.06
    akov
    -0.06
    广ä¹ī
    -0.06
    褥
    -0.06
    ç»ıæµİåľĪ
    -0.06
    çı
    -0.06
    POSITIVE LOGITS
    teman
    0.09
     주ìĨĮ
    0.09
    ä½ıæīĢ
    0.08
     siedz
    0.07
     Addresses
    0.07
    EME
    0.07
    mites
    0.07
    BIND
    0.07
    æľīæĸĻ
    0.07
    å±ħæīĢ
    0.07
    Activations Density 0.068%

    No Known Activations