© 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. 43169
    Prev
    Next
    INDEX
    Explanations

    class or mathematical notation Z

    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
    resta
    -0.08
    okka
    -0.07
    ä¸ŃåĽ½å¤§éĻĨ
    -0.07
    åĪ°æľĢåIJİ
    -0.07
    åħ¨æł¡å¸ĪçĶŁ
    -0.07
    /channel
    -0.07
    aan
    -0.07
    assi
    -0.07
     تک
    -0.07
    çĶµå½±éĻ¢
    -0.07
    POSITIVE LOGITS
     Matcher
    0.07
    æİ°
    0.06
    arks
    0.06
    ä¹Łä¼ļåľ¨
    0.06
    Matches
    0.06
     Benson
    0.06
    顾åIJįæĢĿä¹ī
    0.06
    æĽ´æĺ¯åľ¨
    0.06
    羸åŃIJ
    0.06
     Waste
    0.06
    Activations Density 0.004%

    No Known Activations