© 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. 46643
    Prev
    Next
    INDEX
    Explanations

    wine and vineyards

    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
    ãĥŁãĥ³
    -0.07
    å¯ħ
    -0.07
    ibox
    -0.07
     Katow
    -0.07
    ammad
    -0.07
    奶ç²ī
    -0.07
    åĨ°
    -0.07
    éĻįéĽª
    -0.06
    mie
    -0.06
    æľºåħ³
    -0.06
    POSITIVE LOGITS
    èij¡èIJĦ
    0.12
     grapes
    0.12
     Mediterranean
    0.11
     виногÑĢад
    0.11
     vine
    0.10
    åľ°ä¸Ńæµ·
    0.10
     grape
    0.10
    èij¡èIJĦéħĴ
    0.10
     вино
    0.09
    红éħĴ
    0.09
    Activations Density 0.071%

    No Known Activations