© 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. 8569
    Prev
    Next
    INDEX
    Explanations

    specific types of content

    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
    ä¸Ńåįİæ°ijæĹıä¼Łå¤§å¤įåħ´
    -0.09
    vad
    -0.08
    该éķĩ
    -0.08
    taler
    -0.08
    leben
    -0.07
    QueryString
    -0.07
    pack
    -0.07
    atis
    -0.07
    encial
    -0.07
    yps
    -0.07
    POSITIVE LOGITS
     contempora
    0.07
    å¼ĦèĻļ
    0.06
    积
    0.06
    ä¸įè¿Ľ
    0.06
    sted
    0.06
    éŁ³
    0.06
    راÙħ
    0.06
    æĹłæīĢ
    0.06
    æŁı
    0.06
     Tog
    0.06
    Activations Density 0.099%

    No Known Activations