© 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. 42702
    Prev
    Next
    INDEX
    Explanations

    engine/ing

    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
    gam
    -0.08
     ×IJ׾×Ļ
    -0.07
    esy
    -0.07
    æµ·æ¶Ľ
    -0.06
    å«Į
    -0.06
    thouse
    -0.06
     touching
    -0.06
    笳
    -0.06
    ibe
    -0.06
     exposure
    -0.06
    POSITIVE LOGITS
    æݨåĬ¨ä¸ĭ
    0.12
    ä¸į足以
    0.10
    足以
    0.10
    驱åĬ¨çļĦ
    0.10
    å¼ķ导ä¸ĭ
    0.10
    ä½ľçĶ¨ä¸ĭ
    0.09
    çļĦä½ľçĶ¨ä¸ĭ
    0.09
    ä¿ĥ使
    0.09
    æĮĩ导ä¸ĭ
    0.09
    驱åĬ¨
    0.09
    Activations Density 0.458%

    No Known Activations