© 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. 56334
    Prev
    Next
    INDEX
    Explanations

    cockpit and related vehicle/aviation terms

    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
    åĪĢåĪĥ
    -0.08
    åĽŀé¦ĸ
    -0.07
    路费
    -0.07
    sWith
    -0.07
     repar
    -0.07
    漫æŃ¥
    -0.06
     length
    -0.06
    tester
    -0.06
    locker
    -0.06
    VML
    -0.06
    POSITIVE LOGITS
    æĮĩæĮ¥
    0.12
    åĢ¼çıŃ
    0.11
    è°ĥ度
    0.10
    æݧåĪ¶
    0.09
    å¯ĨåĪĩéħįåIJĪ
    0.09
    abus
    0.09
    æݧåĪ¶çļĦ
    0.09
    æİ¥çıŃ
    0.09
    æݧåĪ¶ä¸Ńå¿ĥ
    0.09
    æĵįä½ľäººåijĺ
    0.09
    Activations Density 0.091%

    No Known Activations