© 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. 4768
    Prev
    Next
    INDEX
    Explanations

    like analogies

    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
    è¿ĻéŨ
    -0.07
    paginate
    -0.07
    示èĮĥåŁºåľ°
    -0.07
    ФС
    -0.07
     sidel
    -0.07
    ¹
    -0.06
    uania
    -0.06
    ách
    -0.06
    Paren
    -0.06
    lund
    -0.06
    POSITIVE LOGITS
     similarly
    0.09
     analogy
    0.09
    åIJĮæł·æĺ¯
    0.08
    ç±»æ¯Ķ
    0.07
     Soph
    0.07
    åIJĮçIJĨ
    0.07
    æ¯Ķåĸ»
    0.07
    łíļ
    0.07
     analogous
    0.07
     analog
    0.07
    Activations Density 0.096%

    No Known Activations