© 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. 46498
    Prev
    Next
    INDEX
    Explanations

    underscore.js

    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
    åĦ¿
    -0.09
    áŁĭ
    -0.08
    ério
    -0.08
    สà¹Į
    -0.08
    à§įথ
    -0.08
    agne
    -0.08
    Ø©
    -0.08
    erval
    -0.08
    upp
    -0.08
    е
    -0.07
    POSITIVE LOGITS
    ical
    0.11
    nya
    0.10
    çļĦ
    0.10
    를
    0.09
    ÑģÑı
    0.09
    ##_
    0.08
    ãģĦ
    0.08
    çļĦãģª
    0.08
    и
    0.08
    able
    0.07
    Activations Density 0.148%

    No Known Activations