© 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. 25938
    Prev
    Next
    INDEX
    Explanations

    learning to do something

    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
    产åĵģæľįåĬ¡
    -0.08
    æµĭè¯ķç»ĵæŀľ
    -0.07
     пÑĢобе
    -0.07
     undefeated
    -0.07
    æķĻåѦçłĶ究
    -0.07
    oter
    -0.06
    åijĪ
    -0.06
    Enums
    -0.06
    äºĭä¸ļåıijå±ķ
    -0.06
    ä»ĺæ¸ħ
    -0.06
    POSITIVE LOGITS
     techniques
    0.11
    è¦ģé¢Ĩ
    0.11
    æĬĢå·§
    0.10
     technique
    0.10
    å¦Ĥä½ķåİ»
    0.09
    æĬĢå·§åĴĮ
    0.09
    驾é©Ń
    0.09
    娴çĨŁ
    0.09
    å¦Ĥä½ķ使çĶ¨
    0.09
    ç²¾æ¹ĽçļĦ
    0.09
    Activations Density 0.241%

    No Known Activations