© 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. 30366
    Prev
    Next
    INDEX
    Explanations

    flour mill or production

    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
    è¿ĩéĩį
    -0.07
    äºĭåıij
    -0.07
    éĥ½ç»Ļ
    -0.07
    licer
    -0.07
    é«ĺ级
    -0.06
    ä»Ģä¹ĪåİŁåĽł
    -0.06
    åĴĮåĬŁèĥ½
    -0.06
    ãģ«èĩ³
    -0.06
    人æĿ¥
    -0.06
    _DEN
    -0.06
    POSITIVE LOGITS
    bai
    0.09
    æī©å±ķèµĦæĸĻ
    0.08
    Symbols
    0.07
    é£ŁãģĦ
    0.07
    -ahead
    0.06
    --------------------------------------------------------------------------------
    0.06
    leftright
    0.06
    eft
    0.06
    ãĤ
    0.06
    æĴij
    0.06
    Activations Density 0.002%

    No Known Activations