© 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. 63535
    Prev
    Next
    INDEX
    Explanations

    connection strings

    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
    æīİå®ŀ
    -0.07
    æ±Ĺæ°´
    -0.07
    ä¸įåıªæĺ¯
    -0.07
    åİļå¾·
    -0.07
    utes
    -0.06
    éĻĮçĶŁäºº
    -0.06
    ä¸įä»ħä»ħ
    -0.06
     sec
    -0.06
    æĿĢæ°Ķ
    -0.06
    æļ´éľ²
    -0.06
    POSITIVE LOGITS
    irtual
    0.09
    èĻļ
    0.09
    _virtual
    0.08
    witz
    0.08
    amai
    0.08
    èĻļæĭŁ
    0.08
    è²ī
    0.08
     Shore
    0.08
    åĬĿéĺ»
    0.08
    èĻļå¹»
    0.08
    Activations Density 0.001%

    No Known Activations