© 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. 12820
    Prev
    Next
    INDEX
    Explanations

    map or dictionary declaration

    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
    åĨĻåľ¨
    -0.07
    zar
    -0.07
    anner
    -0.07
    å¯¹åľ¨
    -0.07
     bundles
    -0.06
    æłĩçļĦ
    -0.06
    ä¹ĭåīįåľ¨
    -0.06
     mạc
    -0.06
    æľīæĦŁ
    -0.06
    çļĦèĭ¦
    -0.06
    POSITIVE LOGITS
    esses
    0.08
    обо
    0.07
    æĮīä¸ĭ
    0.07
    èĦĬ
    0.07
    æľĶ
    0.07
     Ùħشتر
    0.07
    ess
    0.07
    é¹
    0.07
    å°Ķæĸ¯
    0.06
    -toggler
    0.06
    Activations Density 0.087%

    No Known Activations