© 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. 7461
    Prev
    Next
    INDEX
    Explanations

    legal or government titles

    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
    èİħ
    -0.08
    EFE
    -0.07
    InThe
    -0.07
    éĹ®éĹ®
    -0.07
    ee
    -0.06
    éĥ½ä¸į好
    -0.06
    meer
    -0.06
    人们çļĦçĶŁæ´»
    -0.06
    tof
    -0.06
    \n
    -0.06
    POSITIVE LOGITS
     Postar
    0.08
     dated
    0.07
    ateway
    0.07
    ÐĿовоÑģÑĤи
    0.07
    令第
    0.07
    åĽ¾çŃī
    0.07
    ãĢįï¼Ī
    0.07
    igraf
    0.07
     VÃŃc
    0.07
     ÐĵаÑĢан
    0.07
    Activations Density 0.150%

    No Known Activations