© 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. 56425
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and programming imports

    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
    ryn
    -0.08
    eldorf
    -0.08
    ersp
    -0.07
    ensk
    -0.07
    ãĥ¼ãĤ¹
    -0.07
    brio
    -0.07
    éĶ¦æ¶Ľ
    -0.07
    ụt
    -0.07
    enco
    -0.07
    íĴĢ
    -0.07
    POSITIVE LOGITS
    ิà¸ķ
    0.07
    å±Ĥ次
    0.07
    avi
    0.06
    æ±Ĥç²¾
    0.06
    è¿Ľä¸ĢæŃ¥å¢ŀ强
    0.06
     compil
    0.06
    à¸Ľà¸²à¸Ļ
    0.06
    æī
    0.06
    uy
    0.06
    éĤĥ
    0.06
    Activations Density 0.004%

    No Known Activations