© 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. 21477
    Prev
    Next
    INDEX
    Explanations

    physics terms, death, Cornell

    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
    ä¸Ģè¨Ģ
    -0.07
    ajer
    -0.07
    å«Įå¼ĥ
    -0.07
    èĩ´å¯Į
    -0.07
    æĹłè¨Ģ
    -0.06
    -flex
    -0.06
    åĵ¥ä¼¦
    -0.06
    åģ·æĩĴ
    -0.06
    board
    -0.06
     flex
    -0.06
    POSITIVE LOGITS
     sme
    0.08
     reson
    0.08
    çļĦçĶŁåij½
    0.08
     tombe
    0.08
    _death
    0.07
    elin
    0.07
    idup
    0.07
     dissip
    0.07
    èĩªå·±çļĦçĶŁåij½
    0.07
    death
    0.07
    Activations Density 0.003%

    No Known Activations