© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59045
    Prev
    Next
    INDEX
    Explanations

    you may obtain

    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
    Negative Logits
    西æŀĹ
    -0.09
    ersen
    -0.08
    iato
    -0.08
    ä¹Ŀä¹Ŀ
    -0.08
    utta
    -0.08
    à¹ĩà¸Ķ
    -0.07
    -feedback
    -0.07
    imi
    -0.07
    AMPLE
    -0.07
    omma
    -0.07
    POSITIVE LOGITS
     staples
    0.07
    游人
    0.06
     Trait
    0.06
    æļĤæľª
    0.06
     staple
    0.06
    ä»Ģä¹Īéĥ½
    0.06
    婪
    0.06
    ostro
    0.06
    hares
    0.06
     ence
    0.06
    Activations Density 0.004%

    No Known Activations