© 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. 32965
    Prev
    Next
    INDEX
    Explanations

    currency amounts

    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
    追
    -0.07
     op
    -0.06
    ä¹Łä¸įèĥ½
    -0.06
    æıIJæĹ©
    -0.06
    æīĭæķ°
    -0.06
    æį¢
    -0.06
    èIJ¥
    -0.06
     nemmeno
    -0.06
    opa
    -0.06
    åĩĦ
    -0.06
    POSITIVE LOGITS
    ä¸įä½ıçļĦ
    0.08
    éĢļåĪĻ
    0.08
    羣æŃ£
    0.08
    åľ°ä¸º
    0.08
    ä¼ļæł¹æį®
    0.08
    羣æŃ£çļĦ
    0.08
    ixo
    0.08
    羣æŃ£æĪIJ为
    0.08
    ä¼ļ为
    0.08
    å¦Ĥæŀľåĩºçİ°
    0.07
    Activations Density 0.288%

    No Known Activations