© 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. 61281
    Prev
    Next
    INDEX
    Explanations

    dictionaries, Oxford, Bodhi, Times

    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
    亦åı¯
    -0.08
     whilst
    -0.07
    继èĢĮ
    -0.07
    èĢĮç«ĭ
    -0.06
    åĽłèĢĮ
    -0.06
    æĤ£å¤Ħ
    -0.06
    nda
    -0.06
    ãģ¸ãģ¨
    -0.06
    ç§į
    -0.06
    ä¸įåĽł
    -0.06
    POSITIVE LOGITS
    æį®è¯´
    0.09
    æĪijè®°å¾Ĺ
    0.08
    类似éĹ®é¢ĺ
    0.08
    å°±æĽ¾
    0.08
    好åĥıæĺ¯
    0.07
    æĺ¯è¿Ļæł·
    0.07
     reportedly
    0.07
    好åĥı
    0.07
    ä¼ģä¸ļä¸ļåĬ¡
    0.07
    eteor
    0.07
    Activations Density 0.004%

    No Known Activations