© 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. 16116
    Prev
    Next
    INDEX
    Explanations

    for the sake of

    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
    zio
    -0.08
    isper
    -0.07
    äºĨçĦ¶
    -0.07
    Stub
    -0.07
    èĭ¦è¾£
    -0.07
     впл
    -0.07
    evol
    -0.07
    åĪĩç£ĭ
    -0.07
    æĹ¥åIJij
    -0.07
    溫åĴĮ
    -0.07
    POSITIVE LOGITS
     superficial
    0.12
    å½¢å¼ı主ä¹ī
    0.10
    æĹłæķĪ
    0.09
     blindly
    0.09
     gimm
    0.09
     semata
    0.09
     indiscrim
    0.08
    å¾Ĵ
    0.08
    空æ´ŀ
    0.08
     meaningless
    0.08
    Activations Density 0.128%

    No Known Activations