© 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. 37739
    Prev
    Next
    INDEX
    Explanations

    statistical significance

    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
    isse
    -0.08
    apphire
    -0.07
    низ
    -0.07
    éĺµåľ°
    -0.07
    åºĬä¸Ĭ
    -0.07
     aigu
    -0.07
    DateFormat
    -0.07
    enna
    -0.07
    newInstance
    -0.07
    à¸ĵà¹Į
    -0.07
    POSITIVE LOGITS
    æķ£
    0.08
    纲
    0.08
    åıĬåIJĦ
    0.08
     distrib
    0.08
    æĢ»éĩıçļĦ
    0.07
    åĴĮåIJĦ
    0.07
    綱
    0.06
    äºĶèĦı
    0.06
     Schweizer
    0.06
    ä½ĵçļĦ
    0.06
    Activations Density 0.113%

    No Known Activations