© 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. 38945
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and expressions

    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
    åīįæľŁ
    -0.08
    orter
    -0.07
    ç»ıèIJ¥è®¸åı¯è¯ģ
    -0.07
    æľŁä¸Ń
    -0.06
    æľŁåĪĿ
    -0.06
    olid
    -0.06
    å¾
    -0.06
    "
    -0.06
    åīįæľŁçļĦ
    -0.06
     recon
    -0.06
    POSITIVE LOGITS
    zol
    0.08
    èijĽ
    0.07
     kenc
    0.07
    .createObject
    0.07
    üe
    0.07
    lemn
    0.07
    PLE
    0.07
    ìľ
    0.07
    stig
    0.07
    ήμε
    0.07
    Activations Density 0.002%

    No Known Activations