© 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. 29820
    Prev
    Next
    INDEX
    Explanations

    disease namesendings

    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
    en
    -0.08
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
    ugu
    -0.07
    izia
    -0.07
    Ùĩ
    -0.07
    ovima
    -0.07
    enius
    -0.07
    anh
    -0.07
    lett
    -0.07
    <|box_end|>
    -0.07
    POSITIVE LOGITS
    ä»ĭçŁ³
    0.10
    britannien
    0.07
    à¹Į
    0.07
    iseerd
    0.07
    ashtra
    0.07
    ãĥ¡ãĥ³ãĥĪ
    0.07
    ssp
    0.06
    ÙĬØ«
    0.06
    iews
    0.06
     ترÛĮÙĨ
    0.06
    Activations Density 10.130%

    No Known Activations