© 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. 50766
    Prev
    Next
    INDEX
    Explanations

    thinking processes

    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
    adari
    -0.08
    æ°ijå¿ĥ
    -0.08
    çĶŁæ´»æ°´å¹³
    -0.07
    gra
    -0.07
    çİĭå¿Ĺ
    -0.07
    æķĻç§ij书
    -0.07
    customize
    -0.07
    éķľå¤´éĩĮ
    -0.07
     interes
    -0.07
     nomin
    -0.07
    POSITIVE LOGITS
    çģµæĦŁ
    0.11
    è¿ĩç¨ĭ
    0.10
     process
    0.10
    ä¸ĵ注
    0.09
    è¿Ļ个è¿ĩç¨ĭ
    0.09
     processes
    0.09
    è¿ĩç¨ĭçļĦ
    0.09
     workflow
    0.09
     procrast
    0.09
    Process
    0.08
    Activations Density 0.075%

    No Known Activations