© 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. 37842
    Prev
    Next
    INDEX
    Explanations

    showed that

    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
    å°Ķæĸ¯
    -0.08
    ecessarily
    -0.08
    ä¸ĬçĶ¨
    -0.07
     /[
    -0.07
    szak
    -0.07
    _known
    -0.07
    _fore
    -0.07
     fore
    -0.06
     anymore
    -0.06
    身åIJİçļĦ
    -0.06
    POSITIVE LOGITS
     surprisingly
    0.08
     bahwa
    0.08
    æĺ¾èijĹ
    0.08
    ä¸įåIJĮç¨ĭ度çļĦ
    0.08
     significant
    0.08
    /disc
    0.07
    æĥĬ人çļĦ
    0.07
     notably
    0.07
    è¯ģå®ŀ
    0.07
    ezo
    0.07
    Activations Density 0.349%

    No Known Activations