© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 40225
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and code syntax

    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
    ide
    -0.07
    cel
    -0.06
    æĹłäºĭ
    -0.06
    æijĤ
    -0.06
     Mora
    -0.06
    ç»°
    -0.06
     Leon
    -0.06
    uat
    -0.06
    è°·åºķ
    -0.06
    ish
    -0.05
    POSITIVE LOGITS
    öff
    0.07
    è¨İ
    0.07
     bowiem
    0.07
    ffer
    0.07
     неÑĢв
    0.07
    ëĿ¼ëıĦ
    0.07
     Parkway
    0.07
    hares
    0.07
    available
    0.07
    anova
    0.07
    Activations Density 0.001%

    No Known Activations