© 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. 22672
    Prev
    Next
    INDEX
    Explanations

    technical programming terms, programming analogies, or biological terms

    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
    untut
    -0.08
    ouston
    -0.07
    çĤĬ
    -0.07
    æŶæĬ¥
    -0.07
    é¦ģ
    -0.07
    claimer
    -0.07
    acob
    -0.06
     Pela
    -0.06
    zelf
    -0.06
    éķ¿æĮīäºĮç»´çłģ
    -0.06
    POSITIVE LOGITS
    -like
    0.13
    ç±»æ¯Ķ
    0.12
    æł·
    0.12
     analogous
    0.11
     analogue
    0.11
     analogy
    0.11
     equivalent
    0.11
    缸å½ĵäºİ
    0.10
    æł·çļĦ
    0.10
     analog
    0.10
    Activations Density 0.140%

    No Known Activations