© 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. 43308
    Prev
    Next
    INDEX
    Explanations

    chemical reactions and transformations

    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
    æľĪçĶŁ
    -0.08
    çĶ±ä¹Ļæĸ¹
    -0.07
    oire
    -0.07
    eree
    -0.07
    lop
    -0.07
    uat
    -0.06
    éĻį临
    -0.06
    ç¾Į
    -0.06
    ét
    -0.06
    ëłģ
    -0.06
    POSITIVE LOGITS
    转åıĺ为
    0.10
    转åĮĸæĪIJ
    0.09
     undergo
    0.09
    转åĮĸ为
    0.09
    转åĮĸçļĦ
    0.08
    }->{
    0.08
     undergoing
    0.08
     âĨĴ
    0.08
    åıĺæĪIJ
    0.08
     convertirse
    0.07
    Activations Density 0.061%

    No Known Activations