© 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. 1901
    Prev
    Next
    INDEX
    Explanations

    related to specific technologies

    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
    onser
    -0.08
    çıĪ
    -0.08
    è¿ĺåı¯èĥ½
    -0.07
    filt
    -0.07
    åŀĴ
    -0.07
    ä¸Ģæĸ°
    -0.07
    éĥ½æľīåı¯èĥ½
    -0.07
    å¾ħå®ļ
    -0.07
    mine
    -0.07
    liers
    -0.07
    POSITIVE LOGITS
    æŃ£æĺ¯åĽłä¸º
    0.09
    å°±æĺ¯åĽłä¸º
    0.09
     famously
    0.08
    æŃ£æĺ¯åľ¨
    0.08
    æŃ£æĺ¯
    0.08
    èµ·
    0.08
     exempl
    0.08
    å°±æĺ¯éĢļè¿ĩ
    0.08
    å°±æĺ¯æľĢ好çļĦ
    0.08
    ä¾ĭåŃIJ
    0.07
    Activations Density 0.066%

    No Known Activations