© 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. 22904
    Prev
    Next
    INDEX
    Explanations

    short or brief explanations

    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
    ç¼®
    -0.09
    imana
    -0.07
    bere
    -0.07
    åħĪè¿ĽçļĦ
    -0.07
    æݨèįIJç»Ļ
    -0.07
    Ñħождение
    -0.07
    ording
    -0.07
    ingang
    -0.06
    æľĢä½İçļĦ
    -0.06
     trÆ°á»Łng
    -0.06
    POSITIVE LOGITS
     gá»įn
    0.11
    æ¸Ī
    0.08
    ÑĢим
    0.08
    幸
    0.08
    -short
    0.08
    fatt
    0.08
    交æīĢ
    0.07
    ç®ĢçŁŃ
    0.07
    eningen
    0.07
    kk
    0.07
    Activations Density 0.013%

    No Known Activations