© 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. 15324
    Prev
    Next
    INDEX
    Explanations

    online posts or messages

    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
    ض
    -0.09
    ÙĪÙħات
    -0.08
    éĤ£ä¸įæĺ¯
    -0.08
    éĤ£æĺ¯ä¸Ģ个
    -0.08
    éĤ£è¾¹çļĦ
    -0.08
    éĤ£åĦ¿
    -0.08
    Ñĩин
    -0.07
    cent
    -0.07
    éĤ£å¹´
    -0.07
    éĤ£éĤĬ
    -0.07
    POSITIVE LOGITS
     here
    0.10
     aqui
    0.10
    åľ¨è¿ĻéĩĮ
    0.10
    here
    0.09
     herein
    0.09
    åľ¨æѤ
    0.09
     ici
    0.09
     ÑģÑİда
    0.09
     aquÃŃ
    0.09
     اÛĮÙĨجا
    0.09
    Activations Density 1.261%

    No Known Activations