© 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. 40570
    Prev
    Next
    INDEX
    Explanations

    one 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
    è¯Ńè¨ĢåĴĮ
    -0.07
    ãĤīãģĹ
    -0.07
    以åıĬä¸ĢäºĽ
    -0.07
    家åºŃåĴĮ
    -0.07
    одо
    -0.07
    /cop
    -0.07
    everything
    -0.07
    obuf
    -0.07
    adier
    -0.07
    软件åĴĮ
    -0.07
    POSITIVE LOGITS
     either
    0.25
    æĬķèµĦæĪĸ
    0.22
    人æĪĸ
    0.22
     либо
    0.21
    å·¥ä½ľæĪĸ
    0.21
    either
    0.21
    è¦ģä¹Ī
    0.21
    è¦ģä¹Īæĺ¯
    0.20
    æĢ§æĪĸ
    0.20
    å¤įåĪ¶æĪĸ
    0.20
    Activations Density 0.486%

    No Known Activations