© 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. 10824
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming constructs

    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
    æĪ®
    -0.07
     khứ
    -0.06
    æľĢåŁºæľ¬çļĦ
    -0.06
     correlated
    -0.06
    éĻ·å®³
    -0.06
    åı¯ä»¥ä¸į
    -0.06
    imensional
    -0.06
    alculate
    -0.06
    ей
    -0.06
    æģ¤
    -0.06
    POSITIVE LOGITS
    à¤ļà¥įà¤Ľ
    0.07
    icz
    0.07
    øj
    0.07
    )get
    0.07
    )set
    0.07
    åħ¼
    0.07
     }</
    0.07
    zada
    0.07
    ices
    0.07
    '%(
    0.07
    Activations Density 0.002%

    No Known Activations