© 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. 8897
    Prev
    Next
    INDEX
    Explanations

    foreign language and technical terms

    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
    ²
    -0.07
    sequence
    -0.06
    ls
    -0.06
    iewicz
    -0.06
    åĵĴ
    -0.06
    讯
    -0.06
    åı£å¾Ħ
    -0.05
    elas
    -0.05
    ıc
    -0.05
    æľīæĪIJæķĪ
    -0.05
    POSITIVE LOGITS
     appunto
    0.09
    imitive
    0.09
     именно
    0.08
     whichever
    0.08
    æľ¬æĸĩ为åįļ主
    0.08
    emui
    0.08
    PLICIT
    0.08
    /ubuntu
    0.07
    FileVersion
    0.07
    åįİè¯ŀ
    0.07
    Activations Density 0.030%

    No Known Activations