© 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. 39303
    Prev
    Next
    INDEX
    Explanations

    end of expression or list

    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
    nok
    -0.09
    å¿Ĺæĺİ
    -0.08
    åħĭåĬĽ
    -0.08
    ardt
    -0.08
    icher
    -0.07
     غÙĬرÙĩ
    -0.07
    çĥŃéŨæĸĩç«ł
    -0.07
    egr
    -0.07
    æĹ¥åIJİçļĦ
    -0.07
    éĩijéĻµ
    -0.07
    POSITIVE LOGITS
     finally
    0.13
    Finally
    0.11
     finalmente
    0.11
     Finally
    0.11
     infine
    0.10
     schlieÃŁlich
    0.10
     enfin
    0.10
     наконеÑĨ
    0.10
     Finalmente
    0.09
     ÐĿаконеÑĨ
    0.09
    Activations Density 0.058%

    No Known Activations