© 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. 25375
    Prev
    Next
    INDEX
    Explanations

    `using System` or `class` definition

    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
    åĿª
    -0.09
    .cp
    -0.08
    oup
    -0.07
    pell
    -0.07
    elts
    -0.07
    _menus
    -0.07
    жда
    -0.07
    ppi
    -0.07
    appable
    -0.07
    .promise
    -0.07
    POSITIVE LOGITS
     exact
    0.07
    esco
    0.07
     indeed
    0.06
    _USED
    0.06
     exactly
    0.06
     anyway
    0.06
    chner
    0.06
    éģ¨
    0.06
     calcul
    0.06
    wel
    0.06
    Activations Density 0.001%

    No Known Activations