© 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. 51182
    Prev
    Next
    INDEX
    Explanations

    professions

    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
    andbox
    -0.07
    berg
    -0.07
     ëĭ¨ëıħ
    -0.07
    æĪĺçķ¥è§ĦåĪĴ
    -0.07
    èĩªä¹ł
    -0.07
    æĪĺçķ¥æĢ§
    -0.07
     dại
    -0.07
    æĪĺçķ¥çĽ®æłĩ
    -0.06
    æĪĺçķ¥å¸ĥå±Ģ
    -0.06
    èĩªä¸ª
    -0.06
    POSITIVE LOGITS
    为çĶŁ
    0.10
    ä¸īçıŃ
    0.09
     пÑĢоÑĦеÑģÑģии
    0.09
    à¸Ńาà¸Ĭีà¸ŀ
    0.09
    çŃīè¡Įä¸ļ
    0.09
     profissão
    0.09
    è¡Įä¸ļçļĦ
    0.09
     professions
    0.08
    å²Ĺä½įä¸Ĭ
    0.08
     profession
    0.08
    Activations Density 0.387%

    No Known Activations