© 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. 62515
    Prev
    Next
    INDEX
    Explanations

    chemical transition states and intermediates

    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
    æĢ¡
    -0.09
    Bars
    -0.08
     Seger
    -0.08
    æĪIJå¹´
    -0.08
    ittance
    -0.08
    ÙĬدÙĩ
    -0.07
     bachelor
    -0.07
    èĭĹ
    -0.07
    yleft
    -0.07
    agnet
    -0.07
    POSITIVE LOGITS
     stages
    0.08
    段éļİ
    0.08
     intermedi
    0.07
    æĮŁ
    0.07
    -stage
    0.07
    åĮħ饺åŃIJ
    0.07
    ç©
    0.07
    ãĤĴè¿İ
    0.07
    éļİ段
    0.06
    åħĭéļ¾
    0.06
    Activations Density 0.003%

    No Known Activations