© 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. 60212
    Prev
    Next
    INDEX
    Explanations

    turned into, Latter-Day, finally took

    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
    å¯¹ä½łæľī帮åĬ©
    -0.08
    ä¸ĢèĪ¬æĥħåĨµä¸ĭ
    -0.07
    Bas
    -0.07
    ä¸Ģèµ·çİ©
    -0.07
    æł¹æį®éľĢè¦ģ
    -0.07
    ä¸Ģ个æĺŁæľŁ
    -0.07
    ç»ıå¸¸åľ¨
    -0.07
     awesome
    -0.07
    该éķĩ
    -0.07
    以åıĬåħ¶ä»ĸ
    -0.07
    POSITIVE LOGITS
    ¿
    0.08
    лÑij
    0.07
     “
    0.07
    è¿Ļä¸Ģ
    0.07
    ä¸ī代
    0.06
    orex
    0.06
    梨
    0.06
    æĤĦçĦ¶
    0.06
    æ²»
    0.06
    è¿Ī
    0.06
    Activations Density 0.001%

    No Known Activations