© 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. 15671
    Prev
    Next
    INDEX
    Explanations

    terms of sequences

    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
    ianza
    -0.07
    Õ¡Õ°
    -0.07
    è¯ij
    -0.07
    IZZ
    -0.07
    ÃŃnu
    -0.07
    _specs
    -0.07
    kenal
    -0.07
    æ½į
    -0.07
    uel
    -0.07
    IMER
    -0.07
    POSITIVE LOGITS
    åĩ«
    0.07
    絡
    0.07
    rog
    0.07
    .springboot
    0.07
     Reject
    0.06
    ze
    0.06
    Reject
    0.06
    家æĿij
    0.06
    ¹
    0.06
    essaging
    0.06
    Activations Density 0.020%

    No Known Activations