© 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. 45207
    Prev
    Next
    INDEX
    Explanations

    2 the 2

    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
    å¿ĹåĪļ
    -0.07
    è¾ī
    -0.07
    udas
    -0.06
    à¸Ĺัà¸ģษ
    -0.06
    astes
    -0.06
    è¼Ŀ
    -0.06
    å¸ĥé²ģ
    -0.06
     kÃŃn
    -0.06
    çļĦåı«
    -0.06
     Drew
    -0.06
    POSITIVE LOGITS
    ponent
    0.08
     denominator
    0.08
     Aeros
    0.07
    åľ¨åĵªåĦ¿
    0.07
    åİŁçīĪ
    0.07
     numerator
    0.07
    åĪĨ
    0.07
     subtotal
    0.07
    ä½łæĺ¯æĪijçļĦ
    0.07
    elaar
    0.07
    Activations Density 0.002%

    No Known Activations