© 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. 30648
    Prev
    Next
    INDEX
    Explanations

    numbers and 'May'

    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
    åįģäºĮå¹´
    -0.08
    æĢĴ
    -0.08
    ughter
    -0.07
    rš
    -0.07
    usic
    -0.07
     Magn
    -0.06
    åij¨å²ģçļĦ
    -0.06
    ä¹Ŀå¹´
    -0.06
    alach
    -0.06
    以åıĬ对
    -0.06
    POSITIVE LOGITS
    ä¸Ģèĩ³
    0.13
    ä¸ĢäºĮ
    0.11
    ï½ŀ
    0.11
    å·¦åı³
    0.11
    å·¦åı³çļĦ
    0.10
    ä¸ĢåĪ°
    0.10
    หร
    0.10
    æĪĸå¤ļ
    0.10
    ãĢľ
    0.10
    天左åı³
    0.10
    Activations Density 0.611%

    No Known Activations