© 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. 7977
    Prev
    Next
    INDEX
    Explanations

    interval breaks

    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
    强çļĦ
    -0.08
    pty
    -0.08
    phan
    -0.07
    FTA
    -0.07
     ÙĪضع
    -0.07
    .lp
    -0.07
    porter
    -0.07
     billions
    -0.07
    åľ¨åIJĦç§į
    -0.07
    ös
    -0.07
    POSITIVE LOGITS
     interval
    0.09
    åİŁå®ļ
    0.08
     intervals
    0.08
     Interval
    0.08
    åĮºéĹ´
    0.07
    éĹ´éļĶ
    0.07
    interval
    0.07
    Interval
    0.07
    interv
    0.07
    Sampler
    0.07
    Activations Density 0.003%

    No Known Activations