© 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. 15487
    Prev
    Next
    INDEX
    Explanations

    modules or path components

    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
    带åİ»
    -0.07
    ovic
    -0.06
    ä¸įèĥľ
    -0.06
    è¦Ĩ
    -0.06
    aliza
    -0.06
    [sizeof
    -0.06
    /problems
    -0.06
    ä¸įèµ·
    -0.06
    éĶĢåĶ®é¢Ŀ
    -0.06
    ç§Ģæīį
    -0.06
    POSITIVE LOGITS
    ihak
    0.08
    åĪ¹
    0.08
    Ñģло
    0.07
    éĢļåĪĻ
    0.07
    agem
    0.07
     &(
    0.07
    æĴ²
    0.07
    aim
    0.07
    ä»Ģä¹Īæł·çļĦ人
    0.07
    .Fire
    0.07
    Activations Density 0.422%

    No Known Activations