© 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. 58822
    Prev
    Next
    INDEX
    Explanations

    red-sensitive, Jojo

    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
    åľ¨åĨħ
    -0.07
    åľ¨åĨħçļĦ
    -0.07
    agit
    -0.07
    åħ¬åı¸ä¸İ
    -0.06
    OME
    -0.06
    oug
    -0.06
     fan
    -0.06
    aka
    -0.06
    ç»Ļ客æĪ·
    -0.06
    ×Ĵ×Ļ
    -0.06
    POSITIVE LOGITS
    èĢĥéªĮ
    0.08
    eded
    0.07
    大éĥ¨
    0.07
    æĮ½
    0.07
    enas
    0.07
    ulement
    0.07
    ire
    0.07
    anden
    0.07
    Tracks
    0.07
    ammer
    0.07
    Activations Density 0.025%

    No Known Activations