© 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. 14225
    Prev
    Next
    INDEX
    Explanations

    Oxford dictionary definitions

    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
    udir
    -0.07
    ä¸ŃåİŁ
    -0.07
    ofd
    -0.07
    ies
    -0.07
    orgia
    -0.07
    夷
    -0.07
    é«
    -0.07
    hog
    -0.06
    ulant
    -0.06
    ä¸ļ
    -0.06
    POSITIVE LOGITS
     indeed
    0.15
    ç¡®å®ŀæĺ¯
    0.11
    ç¡®å®ŀ
    0.11
    確ãģĭãģ«
    0.10
    Indeed
    0.10
     infatti
    0.10
    ç¡®æľī
    0.09
     Indeed
    0.09
    ãĤĦãģ¯ãĤĬ
    0.08
     дейÑģÑĤвиÑĤелÑĮно
    0.08
    Activations Density 0.011%

    No Known Activations