© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18543
    Prev
    Next
    INDEX
    Explanations

    your following

    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
    ffect
    -0.08
    ANNOT
    -0.07
    aising
    -0.06
    alis
    -0.06
    èµĦæĸĻæĺ¾ç¤º
    -0.06
    ientras
    -0.06
    ä¸įåĪ©å½±åĵį
    -0.06
     azonban
    -0.06
    åĴĮä¿¡æģ¯åĮĸ
    -0.06
    ziali
    -0.06
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.09
     ÙħعÙĬÙĨ
    0.08
     olsa
    0.08
    ebb
    0.08
    ç«Ļç«Ļ
    0.07
    nek
    0.07
    åIJ¦åĪĻä¼ļ
    0.06
    mento
    0.06
    onel
    0.06
    inkin
    0.06
    Activations Density 0.327%

    No Known Activations