© 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. 11778
    Prev
    Next
    INDEX
    Explanations

    catalyzed. cyclization. activation. hydrogenation

    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
     cÃłng
    -0.07
    æĹ©æĻļ
    -0.07
    .fc
    -0.07
    éĩĩåıĸæݪæĸ½
    -0.06
     gour
    -0.06
     Prat
    -0.06
    fc
    -0.06
    è¬
    -0.06
    èĤ´
    -0.06
     examiner
    -0.06
    POSITIVE LOGITS
    Authenticated
    0.09
     novel
    0.08
     orchestrated
    0.08
    æĶ¾è¿ĩ
    0.08
    æĸĩ广
    0.08
    æ±Łæµ·
    0.08
     unprecedented
    0.08
     coined
    0.08
    è¿ĶåĽŀ顶éĥ¨
    0.08
     Harness
    0.08
    Activations Density 0.170%

    No Known Activations