© 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. 14976
    Prev
    Next
    INDEX
    Explanations

    university of

    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
    izou
    -0.07
    queira
    -0.07
    λήÏĤ
    -0.07
    باÙĥ
    -0.07
    ypad
    -0.07
     zase
    -0.07
    boh
    -0.07
    Fabr
    -0.07
    uong
    -0.07
    èī°
    -0.07
    POSITIVE LOGITS
     of
    0.09
    istica
    0.07
     de
    0.07
    arium
    0.07
    à¸Ĺà¹īาย
    0.06
     ÙĩاÛĮ
    0.06
    äºİ
    0.06
     của
    0.06
    ÙĩاÛĮ
    0.06
    à¹ģหà¹Īà¸ĩ
    0.06
    Activations Density 0.484%

    No Known Activations