© 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. 22011
    Prev
    Next
    INDEX
    Explanations

    comparison operators and relative terms

    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
    åĽŀæĿ¥äºĨ
    -0.07
    ÑģÑĤÑı
    -0.07
    ç·ł
    -0.07
     offerts
    -0.06
    ä¹Łæĺ¯æĪij
    -0.06
    ptos
    -0.06
    enek
    -0.06
    acker
    -0.06
    çĽ¸æľĽ
    -0.06
    æ¸Ĭ
    -0.06
    POSITIVE LOGITS
     ÑĥÑģÑĤановленного
    0.07
    azzo
    0.07
    çĦī
    0.07
    æŁIJä¸Ģ
    0.07
    á»ķi
    0.07
    åħ¬è®¤çļĦ
    0.07
     aforementioned
    0.06
    åħ¬å¸ĥçļĦ
    0.06
    产åĵģçĶŁäº§
    0.06
    模å¼ıä¸Ń
    0.06
    Activations Density 0.040%

    No Known Activations