© 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. 26620
    Prev
    Next
    INDEX
    Explanations

    finite fields

    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
    andar
    -0.10
     참조
    -0.09
     nato
    -0.08
    èĢĮçŁ¥
    -0.08
    _ADAPTER
    -0.08
    acap
    -0.08
    glieder
    -0.07
    åī¯ä¼ļéķ¿
    -0.07
    -Series
    -0.07
     reasonably
    -0.07
    POSITIVE LOGITS
    çļĦçݯå¢ĥä¸ĭ
    0.06
    讳
    0.06
    lobber
    0.06
    秽
    0.06
    (Boolean
    0.06
    çݯå¢ĥä¸ĭ
    0.06
    åij½
    0.06
    éĢĨè¡Į
    0.06
    _MISSING
    0.06
    æĭįæīĭ
    0.06
    Activations Density 0.005%

    No Known Activations