© 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. 3893
    Prev
    Next
    INDEX
    Explanations

    phase transition

    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
    адÑĮ
    -0.08
    profil
    -0.08
    æľĪ以æĿ¥
    -0.08
    ä¸į足çļĦ
    -0.08
    ä½¼
    -0.07
    hap
    -0.07
    åŀ£
    -0.07
    被çĽĹ
    -0.07
    ãģĨãģ¡ãģ«
    -0.07
     fournis
    -0.07
    POSITIVE LOGITS
    åıijçĶŁæŶ
    0.08
     occurring
    0.08
     happening
    0.08
    åĪĨæ°´
    0.08
    åıijçĶŁåľ¨
    0.08
     transition
    0.08
     dividing
    0.07
    åıijçĶŁäºİ
    0.07
    çݰ象
    0.07
    çļĦåıijçĶŁ
    0.07
    Activations Density 0.021%

    No Known Activations