© 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. 44811
    Prev
    Next
    INDEX
    Explanations

    local area network (LAN) and subnets

    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
    abat
    -0.08
    æľĪä¸ĭ
    -0.07
    empo
    -0.07
    åĪ°æīĭ
    -0.07
    ä¸įæĿ¥
    -0.07
    lops
    -0.07
    åľ°æĸ¹çļĦ
    -0.07
    ç§ijåѦçłĶ究éĻ¢
    -0.07
    ziv
    -0.07
     erog
    -0.07
    POSITIVE LOGITS
    åħĭç¦ı
    0.07
    åĨħçļĦ
    0.07
    oy
    0.07
    身å¤Ħ
    0.06
    (PC
    0.06
    (ft
    0.06
    º¼
    0.06
    stra
    0.06
    éĶIJæĦıè¿Ľåıĸ
    0.06
    iculum
    0.06
    Activations Density 0.006%

    No Known Activations