© 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. 42826
    Prev
    Next
    INDEX
    Explanations

    foreign or special characters

    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
    wich
    -0.07
    大人们
    -0.07
    æŁ¥çľĭåħ¨éĥ¨
    -0.06
    attan
    -0.06
    ä¸īåħ¬
    -0.06
    é¢Ĩè¢ĸ
    -0.06
    çĥŃçĤ¹æĸ°éĹ»
    -0.06
    à¸ľà¸¹à¹īà¹ĥหà¸įà¹Ī
    -0.06
     landlords
    -0.06
    çļĩ宫
    -0.06
    POSITIVE LOGITS
    ostar
    0.09
    wab
    0.08
    lais
    0.08
    åĴĮåIJĮåѦ
    0.07
    èĦļæŃ¥
    0.07
    æľīæĪIJæķĪ
    0.07
     Peserta
    0.07
    åŃIJå¼Ł
    0.07
    身éĤĬ
    0.07
    åįİ人
    0.07
    Activations Density 0.476%

    No Known Activations