© 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. 3300
    Prev
    Next
    INDEX
    Explanations

    ways to

    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
    Ø©
    -0.11
    ation
    -0.10
    dale
    -0.08
    iels
    -0.08
    RARY
    -0.08
    unyi
    -0.08
    egration
    -0.07
    asilan
    -0.07
    uerta
    -0.07
    cini
    -0.07
    POSITIVE LOGITS
     way
    0.12
    fully
    0.11
    lessly
    0.10
    ward
    0.10
     Weise
    0.09
    以ä¸ĭæĸ¹å¼ı
    0.09
    æĸ¹å¼ıçļĦ
    0.09
    -way
    0.09
    æĸ¹å¼ı
    0.09
    æĸ¹å¼ıè¿Ľè¡Į
    0.09
    Activations Density 0.126%

    No Known Activations