© 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. 40541
    Prev
    Next
    INDEX
    Explanations

    types and declarations

    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
    åIJ¯åıij
    -0.07
    -
    -0.07
    ache
    -0.07
    aupt
    -0.07
    Äįet
    -0.06
    /
    -0.06
    Kenn
    -0.06
    ã
    -0.06
    -server
    -0.06
    .extension
    -0.06
    POSITIVE LOGITS
    æ¹ĥ
    0.09
    çľĭ她
    0.08
     ës
    0.08
     spiagg
    0.08
    InView
    0.08
    abah
    0.08
     brac
    0.08
     Turnbull
    0.08
    ļĮ
    0.08
    _consts
    0.07
    Activations Density 0.135%

    No Known Activations