© 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. 29711
    Prev
    Next
    INDEX
    Explanations

    become everywherediagnoseddamageshortagesexemplifyillustrateswayoccurring

    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
     curated
    -0.10
    Whilst
    -0.10
     realised
    -0.09
    ç®ĹåĬĽ
    -0.08
     Whilst
    -0.08
     canonical
    -0.08
    æĸ°åĨł
    -0.08
     dataset
    -0.08
    å¤įåĪ»
    -0.08
     splitted
    -0.08
    POSITIVE LOGITS
     continually
    0.09
     ÂŃ
    0.08
     someday
    0.07
    æĥŁä¸Ģ
    0.07
     авÑĤома
    0.07
    ãģķãģ¾ãģĸãģ¾ãģª
    0.07
    âĢķ
    0.07
     terrific
    0.07
    æīĢå¼ķèµ·çļĦ
    0.07
    imeo
    0.07
    Activations Density 1.408%

    No Known Activations