© 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. 42489
    Prev
    Next
    INDEX
    Explanations

    UK, true, chr

    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
    ott
    -0.07
    ahari
    -0.06
    zig
    -0.06
    åĬ©äºİ
    -0.06
    æ¯Ĺ
    -0.06
    otar
    -0.06
    çī©åĴĮ
    -0.06
    лиÑĢоваÑĤÑĮ
    -0.06
    lov
    -0.06
    è²łãģij
    -0.06
    POSITIVE LOGITS
    å¤©æ±ł
    0.08
     Graves
    0.08
    eload
    0.08
    ysz
    0.08
    تÙĨا
    0.07
    evos
    0.07
    大æĪIJ
    0.07
    éģ¥
    0.07
    ixin
    0.07
    æ·®
    0.07
    Activations Density 0.004%

    No Known Activations