© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52075
    Prev
    Next
    INDEX
    Explanations

    comparisons of size, quantity, or speed

    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
    Negative Logits
    empo
    -0.08
    çĭ¬
    -0.08
    chos
    -0.07
    èĥ¡ä¹±
    -0.07
    纵
    -0.07
    raig
    -0.07
    大大éĻįä½İ
    -0.07
    æģ°åĪ°å¥½å¤Ħ
    -0.07
    Che
    -0.07
    æĹ
    -0.07
    POSITIVE LOGITS
    à¸ģวà¹Īา
    0.08
    /high
    0.07
    ìŀIJìĿ¸
    0.07
    allest
    0.07
    oen
    0.07
    than
    0.07
     than
    0.07
    Than
    0.07
    -than
    0.07
    igger
    0.06
    Activations Density 0.006%

    No Known Activations