© 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. 16340
    Prev
    Next
    INDEX
    Explanations

    array indexing

    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
    ï¸ı
    -0.08
    ern
    -0.07
    å¦ĤæŀľæĤ¨çļĦ
    -0.07
    ron
    -0.07
    åIJįåѦçĶŁ
    -0.07
    /frame
    -0.07
    es
    -0.07
    ation
    -0.07
    ebb
    -0.07
    (es
    -0.07
    POSITIVE LOGITS
    à¸Ľà¸£à¸°à¸Īำ
    0.08
    usterity
    0.08
    ấp
    0.07
    ÑĥÑģка
    0.07
    sta
    0.07
    uxtap
    0.07
    ippet
    0.07
    ']['
    0.07
    APER
    0.07
    .get
    0.07
    Activations Density 0.015%

    No Known Activations