© 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. 9163
    Prev
    Next
    INDEX
    Explanations

    metal catalysts (iridium, rhodium, ruthenium, cobalt, palladium, molybdenum)

    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
    æł·åŃIJ
    -0.08
    à¹Į
    -0.07
     Bosch
    -0.07
     Glover
    -0.06
     lite
    -0.06
    ë¦Ħ
    -0.06
    è¨Ģ
    -0.06
    ÙĦع
    -0.06
    urve
    -0.06
    æĸľ
    -0.06
    POSITIVE LOGITS
    athom
    0.08
    velt
    0.08
    agro
    0.08
    天ä»Ļ
    0.07
     constructs
    0.07
    å°ı家
    0.07
    chnet
    0.07
     lineHeight
    0.07
    medi
    0.07
    ajo
    0.07
    Activations Density 0.036%

    No Known Activations