© 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. 17607
    Prev
    Next
    INDEX
    Explanations

    r language learning

    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
    æĿł
    -0.08
     Wanted
    -0.07
    گار
    -0.07
    Leading
    -0.07
    markup
    -0.07
    egration
    -0.06
    çĶ¨åħ·
    -0.06
    gre
    -0.06
    祺
    -0.06
    гни
    -0.06
    POSITIVE LOGITS
     global
    0.08
     hon
    0.08
    itter
    0.07
    å¹³
    0.07
    itus
    0.07
    åħ¨å±Ģ
    0.07
    /global
    0.07
    æŶåĪ»
    0.07
    éĢłçļĦ
    0.07
    mund
    0.07
    Activations Density 0.228%

    No Known Activations