© 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. 26481
    Prev
    Next
    INDEX
    Explanations

    that it does 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
     hopefully
    -0.08
     presumably
    -0.08
    èĻ½çĦ¶ä¸įæĺ¯
    -0.08
    ä¸įèĩ³
    -0.07
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    -0.07
    æĹłæ³ķæŃ£å¸¸
    -0.07
     probably
    -0.07
     somewhat
    -0.07
    å¾Īåı¯èĥ½æĺ¯
    -0.07
    edin
    -0.07
    POSITIVE LOGITS
    å¤įåĪ¶æĪĸ
    0.10
    æĸĩ件æĪĸ
    0.10
     necessarily
    0.10
    å°±ä¸Ģå®ļè¦ģ
    0.09
    å°±ä¸Ģå®ļ
    0.09
     непÑĢеменно
    0.09
    æĬķèµĦæĪĸ
    0.09
    ecessarily
    0.09
     nor
    0.08
    人æĪĸ
    0.08
    Activations Density 0.077%

    No Known Activations