© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63097
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code symbols

    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
    é»Ħé¾Ļ
    -0.06
    elus
    -0.06
    acre
    -0.06
    #!
    -0.06
     works
    -0.06
    zos
    -0.06
    باÙĦ
    -0.06
    ional
    -0.06
    åħ¶äºĮ
    -0.06
    bygg
    -0.06
    POSITIVE LOGITS
    æ²½
    0.11
     hird
    0.08
    èIJ©
    0.07
    olato
    0.07
    EME
    0.07
    езда
    0.07
    oleÄį
    0.07
    forth
    0.07
     Oster
    0.07
    uya
    0.07
    Activations Density 0.011%

    No Known Activations