© 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. 14660
    Prev
    Next
    INDEX
    Explanations

    automatically determining

    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¸įåĩı
    -0.08
    ãģĭãģļ
    -0.08
    chner
    -0.08
    çļĦ稳å®ļ
    -0.07
    yron
    -0.07
    稳ä½ı
    -0.07
    enni
    -0.07
    æĺ¯ç»ı
    -0.07
    interrupt
    -0.07
     thiá»ĩp
    -0.07
    POSITIVE LOGITS
     automatically
    0.10
    èĩªåĬ¨çĶŁæĪIJ
    0.09
    èĩªè¡Į
    0.09
    她èĩªå·±
    0.09
     dynamically
    0.09
     discovering
    0.09
     autonom
    0.09
    èĩªä½ľ
    0.09
    èĩªåĬ¨
    0.09
    èĩªåĪĨãģ§
    0.09
    Activations Density 0.277%

    No Known Activations