© 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. 51845
    Prev
    Next
    INDEX
    Explanations

    but not

    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
    èĻ½çĦ¶ä»ĸ
    -0.08
    èĻ½çĦ¶
    -0.08
    ä¸įä½Ĩ
    -0.08
    èĻ½çĦ¶æ²¡æľī
    -0.08
    ç»ĵç¼ĺ
    -0.08
     zwar
    -0.08
    èĻ½çĦ¶åľ¨
    -0.08
    ег
    -0.08
    çĶļèĩ³è¿ŀ
    -0.08
     ugyanis
    -0.08
    POSITIVE LOGITS
    enko
    0.09
     necessarily
    0.08
    ä¸Ģå®ļèĥ½
    0.08
     ones
    0.07
     thereof
    0.07
    Yu
    0.07
     others
    0.07
    çļĦéĤ£ç§į
    0.07
    ool
    0.07
    zik
    0.07
    Activations Density 0.044%

    No Known Activations