© 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. 21797
    Prev
    Next
    INDEX
    Explanations

    convolutional

    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
    ×ķ×¢
    -0.07
    èij±èij±
    -0.07
    intosh
    -0.07
     didik
    -0.07
     Mediter
    -0.07
    tle
    -0.07
    eren
    -0.07
     quo
    -0.07
    noon
    -0.07
    elines
    -0.07
    POSITIVE LOGITS
    æľ¬ç½ijç«Ļ
    0.09
    luan
    0.09
    egend
    0.09
    иден
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    é»į
    0.08
    pedia
    0.08
    aison
    0.08
    блÑİ
    0.08
    lange
    0.08
    Activations Density 0.009%

    No Known Activations