© 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. 50427
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    ogi
    -0.08
    æĺİ
    -0.07
    æľªçĦ¶
    -0.07
     kés
    -0.07
    ÙĨÙĬÙĩ
    -0.07
    ywa
    -0.06
    /spec
    -0.06
    bpp
    -0.06
     casualty
    -0.06
    _backward
    -0.06
    POSITIVE LOGITS
    istin
    0.08
    æµ·éģĵ
    0.08
    令åĴĮ
    0.08
    usso
    0.07
    ileen
    0.07
    ÙĪÙĦØ©
    0.07
     Kast
    0.07
     Kad
    0.07
    äºĮåįģ大
    0.07
    åħļçļĦäºĮåįģ大
    0.07
    Activations Density 0.122%

    No Known Activations