© 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. 12561
    Prev
    Next
    INDEX
    Explanations

    mathematical and physical contexts

    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
    ìłĪ
    -0.08
    acks
    -0.08
    ãĥ¼ãĥŀ
    -0.07
    éĢļå¾Ģ
    -0.07
    樱æ¡ĥ
    -0.07
    ãĥ¼ãĤ¹
    -0.07
     cud
    -0.07
     cú
    -0.07
    árom
    -0.07
    centage
    -0.06
    POSITIVE LOGITS
     Assuming
    0.09
     assuming
    0.09
     assumed
    0.09
    åģĩå®ļ
    0.08
    assuming
    0.08
     assumption
    0.08
     assumes
    0.08
     negligible
    0.08
    åģĩ设
    0.08
    没æľīåħ¶ä»ĸ
    0.08
    Activations Density 0.013%

    No Known Activations