© 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. 56600
    Prev
    Next
    INDEX
    Explanations

    code file beginnings

    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
    emplace
    -0.08
    ä¸įéĸĭ
    -0.07
    <Option
    -0.07
    voire
    -0.07
    é£İæµģ
    -0.07
    /goto
    -0.07
    æľ¬æĬ¥è®°èĢħ
    -0.07
    ìĸ´ëĤĺ
    -0.07
    寶è²Ŀ
    -0.07
    ->$
    -0.07
    POSITIVE LOGITS
     [âĢ¦
    0.11
     [âĢ¦]
    0.10
     (âĢ¦)
    0.10
     âĢ¦
    0.09
     ......
    0.09
     [...]
    0.09
    âĢ¦âĢ¦
    0.09
     (...)
    0.09
     ....
    0.08
    âĢ¦âĢ¦âĢ¦âĢ¦
    0.08
    Activations Density 3.339%

    No Known Activations