© 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. 9379
    Prev
    Next
    INDEX
    Explanations

    reacting radicals and transfer

    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
    ibur
    -0.07
    鸥
    -0.07
    夫åŃIJ
    -0.07
     extrad
    -0.07
    жев
    -0.06
    bauer
    -0.06
     вда
    -0.06
    鼶鼶
    -0.06
     tamp
    -0.06
     reconstruction
    -0.06
    POSITIVE LOGITS
    åĽŀåIJĪ
    0.08
    ä¸ĭä¸Ģ个
    0.08
    æİ¥åĬĽ
    0.08
    å°¾
    0.08
    åĨįæİ¥
    0.08
     chaining
    0.08
    æĶ¾åĩº
    0.08
    ä¸ĭä¸ĢæŃ¥
    0.08
     chain
    0.07
     berikutnya
    0.07
    Activations Density 0.005%

    No Known Activations