© 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. 31130
    Prev
    Next
    INDEX
    Explanations

    chemical names and quantities

    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
     Chambers
    -0.09
    Lite
    -0.08
    çĿ¦
    -0.07
    å¦ĤæŀľçľŁçļĦ
    -0.07
    kot
    -0.07
     pare
    -0.06
    &R
    -0.06
     petró
    -0.06
    çĻ½å¤ľ
    -0.06
     Chamber
    -0.06
    POSITIVE LOGITS
     counting
    0.08
    å¹³åĿĩæ¯ı
    0.08
    aved
    0.08
    åħ¨éĥ¨çļĦ
    0.07
    USAGE
    0.07
    jons
    0.07
    ouser
    0.07
     mol
    0.07
     Count
    0.07
    æĹłéĻħ
    0.07
    Activations Density 0.005%

    No Known Activations