© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22852
    Prev
    Next
    INDEX
    Explanations

    asked if someone

    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
    æĹ¢çĦ¶
    -0.08
    æĹ¢çĦ¶æĺ¯
    -0.08
    æĹ¢è¦ģ
    -0.08
    åħĪæĬĬ
    -0.07
    èĽĨ
    -0.07
    ê»ı
    -0.07
    ç´¢æĢ§
    -0.07
     enfin
    -0.07
    æĹ©çŁ¥éģĵ
    -0.06
    оÑħо
    -0.06
    POSITIVE LOGITS
    ä»»ä½ķä¸Ģ个
    0.10
    å°±ä¼ļåıijçİ°
    0.09
    éļı便
    0.09
     Anyone
    0.09
     cualquiera
    0.09
    çļĦè¯Ŀ
    0.09
    ä»»æĦı
    0.09
    ä»įèĥ½
    0.09
    ä½łå°±èĥ½
    0.08
    çļĦ話
    0.08
    Activations Density 0.413%

    No Known Activations