© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30188
    Prev
    Next
    INDEX
    Explanations

    file formats (xls, doc, ppt)

    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
    ary
    -0.07
     unp
    -0.07
     unc
    -0.07
    濯
    -0.06
    æľ¬ç«Ļ
    -0.06
    sem
    -0.06
    äk
    -0.06
    åħĭç¦ı
    -0.06
    ldb
    -0.06
    ref
    -0.06
    POSITIVE LOGITS
    èĤ¡ä¸ľåıĬ
    0.08
    füg
    0.08
    orta
    0.07
    æĬijæĪĸ
    0.07
    oty
    0.07
    åħ¬åı¸åıĬ
    0.07
     DÃŃky
    0.07
     maupun
    0.07
    é¦Ļæ°Ľ
    0.07
    ahr
    0.07
    Activations Density 0.180%

    No Known Activations