© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41655
    Prev
    Next
    INDEX
    Explanations

    different, same, dependent, general

    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
    ä¸įåĪĨ
    -0.10
    arrass
    -0.08
    ä¸įæĢ¥
    -0.08
    ertes
    -0.08
    åľ¾
    -0.08
    HER
    -0.08
    ä¸įæĦģ
    -0.08
    éĢĨãģ«
    -0.08
    erti
    -0.08
    é£İè½»
    -0.07
    POSITIVE LOGITS
    unless
    0.10
     unless
    0.09
    æĺ¯ä¸įåIJĮçļĦ
    0.09
     âīł
    0.09
    ä¸įçŃīäºİ
    0.08
    ä¸įæĺ¯ä½ł
    0.08
    ä¸įæĺ¯ä¸Ģ个
    0.08
    å°±ä¸įæĺ¯
    0.08
    åľ¨ä¸įåIJĮçļĦ
    0.08
     Unless
    0.08
    Activations Density 0.025%

    No Known Activations