© 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. 12894
    Prev
    Next
    INDEX
    Explanations

    academic fields and 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
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.09
    åĴĮåIJĮäºĭ
    -0.08
    lessly
    -0.08
    éro
    -0.07
    дж
    -0.07
    åıĹæ½®
    -0.07
    alow
    -0.07
    aldi
    -0.07
    ä¸įä¸Ģ
    -0.07
    使çĶ¨åīį
    -0.07
    POSITIVE LOGITS
    ä¸ĢéŨ
    0.08
     courses
    0.08
     sciences
    0.08
     graduates
    0.08
     graduating
    0.08
    ç±»çļĦ
    0.07
    .linkedin
    0.07
    çŃī缸åħ³ä¸ĵä¸ļ
    0.07
     ÑģпеÑĨиалÑĮноÑģÑĤи
    0.07
     majors
    0.07
    Activations Density 0.257%

    No Known Activations