© 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. 63689
    Prev
    Next
    INDEX
    Explanations

    noting or stating facts

    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
    称å¾Ĺä¸Ĭ
    -0.06
    rene
    -0.06
     تÙĤرÙĬب
    -0.06
    igue
    -0.06
    çļĦæķħäºĭ
    -0.06
    æĪijæĺİçĻ½äºĨ
    -0.06
    åı¯ä»¥è¯´
    -0.06
    æ¼Ķç»İ
    -0.06
    iable
    -0.06
    羣çļĦ
    -0.06
    POSITIVE LOGITS
     differences
    0.11
     similarities
    0.11
     discrepancies
    0.10
    注æĦıåĪ°
    0.10
     Unterschiede
    0.10
    å¿ħ须注æĺİ
    0.10
    以ä¸ĭåĩłçĤ¹
    0.09
     inconsistencies
    0.09
    ayne
    0.09
     noted
    0.09
    Activations Density 0.072%

    No Known Activations