© 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. 22569
    Prev
    Next
    INDEX
    Explanations

    (V oxidation states

    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
     Tiny
    -0.08
    .ny
    -0.08
    tiny
    -0.07
    æĿİ大
    -0.07
    IMIT
    -0.07
    éĻķåĮĹ
    -0.07
    INY
    -0.07
    æľĶ
    -0.07
    shire
    -0.06
    imizer
    -0.06
    POSITIVE LOGITS
    åĽĽéĿ¢
    0.08
     Toilet
    0.08
     oxid
    0.08
     oxidation
    0.07
    unc
    0.07
    产åĵģä»·æł¼
    0.07
    å¼Ģåıij票
    0.07
    ogos
    0.07
    æĹħ游度åģĩåĮº
    0.07
     ür
    0.07
    Activations Density 0.018%

    No Known Activations