© 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. 26558
    Prev
    Next
    INDEX
    Explanations

    return Vector, $options, or .return, Vector, $options

    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
    èµ·çļĦ
    -0.07
    ilding
    -0.07
    æ·±
    -0.07
    eof
    -0.07
     Deep
    -0.07
    P
    -0.07
    ench
    -0.07
    {|
    -0.07
    kaar
    -0.07
    cv
    -0.06
    POSITIVE LOGITS
    çĿ
    0.08
    unesse
    0.08
    è´¢è¿IJ
    0.07
    ä»İè¿Ļ个
    0.07
    á»IJ
    0.07
     بÙĩذا
    0.07
    èĬĭ
    0.07
    åŀ¢
    0.07
    ught
    0.07
    çŁ
    0.07
    Activations Density 0.001%

    No Known Activations