© 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. 14846
    Prev
    Next
    INDEX
    Explanations

    phrases with common endings

    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
    çŁ¥çļĦ
    -0.06
    éĹ»
    -0.06
    itm
    -0.06
    éļĶ
    -0.06
    .labels
    -0.06
    .Reader
    -0.06
    é¢Ĺç²Ĵ
    -0.06
    èģŀ
    -0.06
     Mark
    -0.06
     Set
    -0.06
    POSITIVE LOGITS
    iliz
    0.09
    é£İæĻ¯çº¿
    0.07
    æĮĩ导建议
    0.07
     Pellegr
    0.07
    WEBPACK
    0.07
    梦éĩĮ
    0.07
    æīĢå±ŀåĪĨç±»
    0.07
    ¬¸
    0.07
    è¿ĺæľīå°±æĺ¯
    0.07
    /native
    0.07
    Activations Density 0.023%

    No Known Activations