© 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. 18221
    Prev
    Next
    INDEX
    Explanations

    boundary, sequence, supports

    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
     اÙĦإج
    -0.08
    butt
    -0.07
     باب
    -0.07
    ç³»ç»Łåľ¨
    -0.07
    erus
    -0.07
    æѤåĪ»
    -0.06
    éĤ£åIJį
    -0.06
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    -0.06
    éĿ¢æľĿ
    -0.06
    åľ¨æ±½è½¦
    -0.06
    POSITIVE LOGITS
     ÙĪعÙĦÙī
    0.09
    以å¤ĸçļĦ
    0.09
     entirety
    0.07
    eyond
    0.07
    æĪijåı¯æĺ¯
    0.07
    åĴĮæľªæĿ¥
    0.07
     ×ķ×ij
    0.07
    undry
    0.07
    çĤ¹è¿ĻéĩĮ
    0.07
     ÙĪÙģÙĬ
    0.06
    Activations Density 0.007%

    No Known Activations