© 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. 44470
    Prev
    Next
    INDEX
    Explanations

    locations and organizations

    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
    å¹½
    -0.09
    оÑĢÑĥ
    -0.08
    éĻĮ
    -0.07
    JE
    -0.07
    _TLS
    -0.07
    aps
    -0.07
     Eppure
    -0.07
    ä¸İåĽ½åĨħ
    -0.07
    college
    -0.07
     imperson
    -0.07
    POSITIVE LOGITS
    çļĦåIJĪåIJĮ
    0.07
    inta
    0.07
    éĨį
    0.07
    arque
    0.06
    atcher
    0.06
    ette
    0.06
    饱
    0.06
    ç»ĦåĽ¾
    0.06
    éłĵ
    0.06
    å¤Ł
    0.06
    Activations Density 0.137%

    No Known Activations