© 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. 33738
    Prev
    Next
    INDEX
    Explanations

    carrier or agent

    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
    ä½ľä¸ºä¸Ģ项
    -0.09
    åģļ为
    -0.08
     compi
    -0.08
    è°ĵä¹ĭ
    -0.08
    ä½ľä¸º
    -0.08
     sebagai
    -0.07
    åģļçĤº
    -0.07
    à¹ĥหà¹īà¹Ģà¸Ľà¹ĩà¸Ļ
    -0.07
    ä½ľçĤº
    -0.07
    atoires
    -0.07
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.10
     sekaligus
    0.09
     bagi
    0.08
    ä¹ĭä¸ĢçļĦ
    0.08
    меÑģÑĤи
    0.08
    .realpath
    0.08
     for
    0.08
     extraordinaire
    0.08
    ersatz
    0.07
    åħ¼
    0.07
    Activations Density 0.303%

    No Known Activations