© 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. 57492
    Prev
    Next
    INDEX
    Explanations

    items in a collection or list

    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
     ensuing
    -0.09
    æĬĺä¸į
    -0.08
    以æѤæĿ¥
    -0.07
    çĦ¶åIJİéĢļè¿ĩ
    -0.07
    åıįåĢĴ
    -0.07
    æĹĭé£İ
    -0.07
    继èĢĮ
    -0.07
    缸åºĶ
    -0.07
    è¯ģå®ŀåħ¶
    -0.07
    å¤ļæĿ¡
    -0.07
    POSITIVE LOGITS
     consists
    0.10
    çļĦçī¹çĤ¹æĺ¯
    0.10
     infatti
    0.09
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    0.09
    æĹłéĿŀ
    0.08
     obviously
    0.08
    åĪĨ为
    0.08
    主è¦ģåĮħæĭ¬
    0.08
    æĺ¾çĦ¶æĺ¯
    0.08
     consist
    0.08
    Activations Density 0.072%

    No Known Activations