© 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. 14287
    Prev
    Next
    INDEX
    Explanations

    division or fraction

    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
    æİ¥çĿĢ
    -0.06
    ta
    -0.06
    ost
    -0.06
    itty
    -0.06
    opoulos
    -0.06
    ä¸ĭ次
    -0.06
    ARI
    -0.06
    çݯå¢ĥå½±åĵįè¯Ħä»·
    -0.06
    BUS
    -0.05
    è¶ħ
    -0.05
    POSITIVE LOGITS
    ))/(
    0.09
    è¿Ļä¸ĢåĪ»
    0.09
    ÙĪرش
    0.08
    )/(
    0.08
    USTER
    0.08
    uster
    0.08
    èĭĹ
    0.07
     patrimoni
    0.07
    æ®ĸ
    0.07
    人çļĦçĶŁåij½
    0.07
    Activations Density 0.004%

    No Known Activations