© 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. 31310
    Prev
    Next
    INDEX
    Explanations

    drastically leads to

    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
    ¹
    -0.08
    Ñħо
    -0.08
    iversal
    -0.07
    åı¯æĺ¯åľ¨
    -0.07
    ousel
    -0.07
    enty
    -0.07
    nolo
    -0.07
    пил
    -0.07
    lett
    -0.07
    cks
    -0.07
    POSITIVE LOGITS
    ly
    0.09
    èĩªå·±è¢«
    0.09
    严éĩįåIJİæŀľ
    0.08
    ä¸Ģæĸij
    0.08
    æĹłæ³ķæŃ£å¸¸
    0.08
     ìĿ¸íķ´
    0.08
    çļĦåİŁåĽłä¹ĭä¸Ģ
    0.08
    çļĦåİŁåĽłæĺ¯
    0.08
    人说
    0.07
    UGHT
    0.07
    Activations Density 0.001%

    No Known Activations