© 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. 4574
    Prev
    Next
    INDEX
    Explanations

    include or add information/content

    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
    æĽ¿å°¼
    -0.09
    çĶ¨æĪ·ä¸Ĭä¼ł
    -0.07
    WithError
    -0.07
    ạng
    -0.07
    ensch
    -0.07
    对å¾ħ
    -0.07
    ÙĬبة
    -0.07
    è¿ĪçĿĢ
    -0.07
    yster
    -0.07
     ÑĪÑĤÑĥка
    -0.07
    POSITIVE LOGITS
    å¿ħè¦ģçļĦ
    0.09
    å¿ħè¦ģ
    0.08
     references
    0.08
     indications
    0.07
    å¦Ĥä¸ĭ
    0.07
    åħ³äºİ
    0.07
     indication
    0.07
     поÑıÑģ
    0.07
    对ä¸įåIJĮ
    0.07
    æĽ´å¤ļ
    0.07
    Activations Density 0.025%

    No Known Activations