© 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. 23845
    Prev
    Next
    INDEX
    Explanations

    carbon dioxide, oxygen, compounds

    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
    bare
    -0.07
    	gen
    -0.07
    åĪļåĪ°
    -0.07
    åĨįæİ¥åĨį
    -0.07
    æĽ´ä¸Ĭä¸Ģå±Ĥ楼
    -0.07
    anya
    -0.07
     filetype
    -0.07
    opak
    -0.07
    isNew
    -0.07
    èĸ°
    -0.07
    POSITIVE LOGITS
    Stamped
    0.08
     harmless
    0.07
    ijk
    0.07
    ä½ĵ积
    0.07
    èħ¾
    0.07
     visibly
    0.07
    å¤ļèĬ¬
    0.07
    éĩĬæĶ¾åĩº
    0.07
    /_
    0.07
     debris
    0.07
    Activations Density 0.036%

    No Known Activations