© 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. 57779
    Prev
    Next
    INDEX
    Explanations

    optimal control problems

    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
    æį¢ç®Ĺ
    -0.08
     REFER
    -0.08
     preval
    -0.08
    onto
    -0.08
    :`~
    -0.08
    å¼Ģæľį
    -0.08
     bleed
    -0.08
    é«ĺä¸ĵ
    -0.08
    èŀįèŀį
    -0.07
    loom
    -0.07
    POSITIVE LOGITS
     lenght
    0.07
     length
    0.07
     Length
    0.07
    è¿IJåĬ¨
    0.07
    éķ¿åº¦çļĦ
    0.07
    ä¿®æĶ¹
    0.07
     lengths
    0.07
    length
    0.06
     drag
    0.06
     wys
    0.06
    Activations Density 0.003%

    No Known Activations