© 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. 32375
    Prev
    Next
    INDEX
    Explanations

    TEMPLATE, input, list, URL, right

    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
    -files
    -0.07
    æĿ¥äºº
    -0.07
    ids
    -0.07
    jes
    -0.07
    -drive
    -0.06
    çijķ
    -0.06
    roups
    -0.06
     má»Ļng
    -0.06
    å¼±åĮĸ
    -0.06
    -marker
    -0.06
    POSITIVE LOGITS
     Affero
    0.08
    åĬ¡
    0.07
    ábado
    0.07
    anagan
    0.07
     Willis
    0.06
    Mutex
    0.06
    çļĪ
    0.06
    omics
    0.06
    ney
    0.06
    авли
    0.06
    Activations Density 0.106%

    No Known Activations