© 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. 55250
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms

    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
     unp
    -0.08
    vig
    -0.07
    æ¾İ
    -0.07
    возмо
    -0.07
    velle
    -0.06
    /V
    -0.06
    atas
    -0.06
    tg
    -0.06
    chein
    -0.06
    zimmer
    -0.06
    POSITIVE LOGITS
    å°Ķåħĭ
    0.07
    åħįè´¹éĺħ读
    0.07
    æĬĬè¿Ļ个
    0.07
    лок
    0.07
    λλα
    0.07
    å®Ŀé¾Ļ
    0.07
    æĥħ
    0.07
    èĤ©ä¸Ĭ
    0.07
    oomla
    0.07
    两份
    0.07
    Activations Density 0.060%

    No Known Activations