© 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. 13256
    Prev
    Next
    INDEX
    Explanations

    recent times and modern eras

    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
    çŃīä¼łç»Ł
    -0.08
    ĥģ
    -0.08
    åĪĿæģĭ
    -0.08
    æ·±å¤ĦçļĦ
    -0.08
    æ·±å¤Ħ
    -0.08
    åĦ¿æŶ
    -0.08
    åİŁæĿ¥æĺ¯
    -0.08
    غاÙħ
    -0.07
    çİĩåħĪ
    -0.07
    é¦Ī
    -0.07
    POSITIVE LOGITS
    modern
    0.14
     modern
    0.14
    Modern
    0.13
    çݰ代çļĦ
    0.13
     Modern
    0.12
    çݰ代
    0.12
     moderne
    0.12
     اÙĦØŃدÙĬثة
    0.12
    æĺ¯çݰ代
    0.12
    çļĦçݰ代
    0.11
    Activations Density 0.209%

    No Known Activations