© 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. 22493
    Prev
    Next
    INDEX
    Explanations

    legacy systems and traditional words

    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
    纳米
    -0.08
    á»Ńng
    -0.07
    Montserrat
    -0.07
    æĹłçijķ
    -0.07
    ãģ°ãģĭãĤĬ
    -0.07
    fé
    -0.07
    ÅŁa
    -0.07
    èµ
    -0.07
    aub
    -0.07
    minecraft
    -0.06
    POSITIVE LOGITS
    ä¼łç»ŁçļĦ
    0.22
    ä¼łç»Ł
    0.22
     traditional
    0.21
    çŃīä¼łç»Ł
    0.21
    çļĦä¼łç»Ł
    0.21
     legacy
    0.18
     Traditional
    0.18
    èĢģçīĮ
    0.18
    legacy
    0.18
    Traditional
    0.17
    Activations Density 1.300%

    No Known Activations