© 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. 15676
    Prev
    Next
    INDEX
    Explanations

    第ä¸Ģç«ł, ç¬¬åĽĽç«ł, 第äºĮ次, ç«ł

    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
    Ø©
    -0.11
    ãĤ£
    -0.10
    翼翼
    -0.09
    év
    -0.09
    èĢĮåIJĮ
    -0.09
    ively
    -0.09
    ivec
    -0.09
    ebbe
    -0.09
    nyder
    -0.09
    ħ
    -0.08
    POSITIVE LOGITS
    åĴĮ第äºĮ
    0.09
    é©Ł
    0.08
    jenigen
    0.08
     ÙĪاÙĦØ«
    0.08
    -most
    0.07
    udas
    0.07
    allas
    0.07
    atismo
    0.06
    ra
    0.06
    ä¸ĸçķĮ大æĪĺ
    0.06
    Activations Density 0.004%

    No Known Activations