© 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. 13495
    Prev
    Next
    INDEX
    Explanations

    creative work by

    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
    çĦ¶å¤§
    -0.08
    ãģ°ãģĭãĤĬ
    -0.07
    ä¸įæĺ¯ä¸Ģ个
    -0.07
    æīĢèĥ½
    -0.07
    次ä¼ļè®®
    -0.07
    pared
    -0.07
    é¢Ħéĺ²ä¸ºä¸»
    -0.06
    InRange
    -0.06
     staple
    -0.06
    евиÑĩ
    -0.06
    POSITIVE LOGITS
    åı¦æľī
    0.08
    åįıåĬĽ
    0.08
    çĶ±ä¸ŃåĽ½
    0.08
    æĸ¹èĪŁ
    0.08
    ä¸į详
    0.07
    åĪĻçĶ±
    0.07
    åıĬ产åĵģ
    0.07
    æĿ¥èĩªä¸ŃåĽ½
    0.07
    åĿĩæĿ¥èĩª
    0.07
    åħ¼
    0.07
    Activations Density 0.620%

    No Known Activations