© 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. 44231
    Prev
    Next
    INDEX
    Explanations

    and then

    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
    ä¼ģä¸ļåħ³ç³»
    -0.08
    æī¬å¸Ĩ
    -0.07
    ful
    -0.07
    áni
    -0.07
    utin
    -0.07
    æĺ¥åįİ
    -0.07
    iaga
    -0.07
    /forum
    -0.07
    à§ģà¦ķ
    -0.07
    amay
    -0.07
    POSITIVE LOGITS
     then
    0.13
    çĦ¶åIJİ
    0.11
    then
    0.10
    çĦ¶åIJİåľ¨
    0.10
     subsequently
    0.09
     thereby
    0.09
    çĦ¶åIJİåĨį
    0.09
     kemudian
    0.09
    Then
    0.08
    ä»İèĢĮ
    0.08
    Activations Density 0.177%

    No Known Activations