© 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. 8392
    Prev
    Next
    INDEX
    Explanations

    form

    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
     ridden
    -0.08
    ÏĨι
    -0.08
    ازÛĮ
    -0.07
    fed
    -0.07
    obox
    -0.07
    abin
    -0.07
     sär
    -0.07
    æ¶Īè´¹èĢħæĿĥçĽĬ
    -0.06
    ษ
    -0.06
     ngại
    -0.06
    POSITIVE LOGITS
    á»ĥn
    0.08
    ç²ĺ
    0.07
    éĺ²åŁİ
    0.07
    cps
    0.07
     Breit
    0.07
     Bett
    0.07
     broad
    0.07
     promis
    0.07
     Broad
    0.07
    emar
    0.07
    Activations Density 0.002%

    No Known Activations