© 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. 18640
    Prev
    Next
    INDEX
    Explanations

    graphics/shader/code setup

    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
    uter
    -0.08
    ÙģØ´
    -0.08
    pageTitle
    -0.08
    /pay
    -0.08
    cott
    -0.08
     seedu
    -0.08
    Mixin
    -0.08
    utor
    -0.08
    ä»Ģä¹Īäºĭ
    -0.07
    czyk
    -0.07
    POSITIVE LOGITS
     APIs
    0.06
    å·Ŀ
    0.06
    ids
    0.06
     API
    0.06
    æ©
    0.06
    åĪĽå»º
    0.06
    æŦ
    0.06
     wait
    0.06
    -supported
    0.06
    idl
    0.06
    Activations Density 0.230%

    No Known Activations