© 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. 44578
    Prev
    Next
    INDEX
    Explanations

    true or false

    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
    çī¹å°Ķ
    -0.08
    itin
    -0.07
    ĮĢ
    -0.07
    çIJĨ论水平
    -0.07
    akkan
    -0.07
    ابÛĮ
    -0.07
    ieh
    -0.06
    usi
    -0.06
    è²Ĥ
    -0.06
    ç«ĻåĨħæIJľç´¢
    -0.06
    POSITIVE LOGITS
    对éĶĻ
    0.09
    /false
    0.09
    æĺ¯åIJ¦æŃ£ç¡®
    0.08
    false
    0.08
     False
    0.08
    pha
    0.08
    (True
    0.08
    åĪ¤æĸŃé¢ĺ
    0.08
     false
    0.08
    False
    0.08
    Activations Density 0.011%

    No Known Activations