© 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. 59127
    Prev
    Next
    INDEX
    Explanations

    all, pairs, players, elements, races, pH, week

    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
    Negative Logits
    äºĨåĩºæĿ¥
    -0.07
    allery
    -0.07
    好åIJĥ
    -0.07
    缸æ¯Ķä¹ĭä¸ĭ
    -0.07
    iele
    -0.07
    ä¸į容
    -0.07
     aside
    -0.06
    gues
    -0.06
    好æĥ³
    -0.06
    FUNC
    -0.06
    POSITIVE LOGITS
    gens
    0.08
     hinweg
    0.08
    mers
    0.07
    æĹłç©·çļĦ
    0.07
    taus
    0.07
    wares
    0.07
    quals
    0.07
    éĩıåĬĽ
    0.07
    失æģĭ
    0.06
    ç»Īäºİ
    0.06
    Activations Density 0.005%

    No Known Activations