© 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. 15976
    Prev
    Next
    INDEX
    Explanations

    characterization and format

    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
    åĽº
    -0.07
    ัà¹Īว
    -0.07
    å¾Ĵæīĭ
    -0.07
    á»Ŀ
    -0.06
    èģļéĽĨ
    -0.06
    å¹¼
    -0.06
    latan
    -0.06
    彦
    -0.06
    antu
    -0.06
    å®ŀä½ĵ
    -0.06
    POSITIVE LOGITS
    olla
    0.08
    ussi
    0.08
    æłĩåĩĨè¦ģæ±Ĥ
    0.07
    å¾Ĺæ°´
    0.07
    masuk
    0.07
    åįķä½įåıĤåĬł
    0.07
    ugged
    0.07
    ernational
    0.07
    _INET
    0.07
    ×ĺר
    0.07
    Activations Density 0.202%

    No Known Activations