© 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. 3439
    Prev
    Next
    INDEX
    Explanations

    completion of a process

    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
    ekar
    -0.09
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.08
    ouro
    -0.08
     ums
    -0.08
     totiž
    -0.08
    æľīä¸ĭåĪĹ
    -0.08
    udid
    -0.08
    hver
    -0.07
    ouri
    -0.07
    ãĢģãĢĮ
    -0.07
    POSITIVE LOGITS
    illa
    0.07
     optionally
    0.07
    г
    0.07
     ÑģобÑģÑĤвенно
    0.07
     finally
    0.07
    两èĢħ
    0.07
    åĨįåĬłä¸Ĭ
    0.06
    emu
    0.06
    å¾Ĺåĩºç»ĵ论
    0.06
    æľĢåIJİæĺ¯
    0.06
    Activations Density 0.017%

    No Known Activations