© 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. 27648
    Prev
    Next
    INDEX
    Explanations

    conditional or logical statements

    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
    auen
    -0.08
    尼奥
    -0.07
    主è¦ģåĪĨ为
    -0.07
    æĹ¢åı¯
    -0.07
     íĺķíĥľ
    -0.07
    æĹ¢ä¸į
    -0.07
    ä¸Ģç§įæĺ¯
    -0.06
    (&:
    -0.06
    .real
    -0.06
    «
    -0.06
    POSITIVE LOGITS
    满足
    0.08
     forall
    0.08
    æ¯ıå½ĵ
    0.08
     whenever
    0.08
     Condition
    0.08
    ساÙĨ
    0.07
    对äºİè¿ĻäºĽ
    0.07
     condition
    0.07
     Conditioning
    0.07
    åŃĺåľ¨çĿĢ
    0.07
    Activations Density 0.012%

    No Known Activations