© 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. 51437
    Prev
    Next
    INDEX
    Explanations

    further research or study needed

    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
    åĽŀçŃĶéĹ®é¢ĺ
    -0.07
     sẵn
    -0.06
    aket
    -0.06
    æīĢåľ¨çļĦ
    -0.06
    æ¯Ķä½ł
    -0.06
    ä½łä¸į
    -0.06
    ä½¿ä½ł
    -0.06
    æ´¾éģ£
    -0.06
    åĢ
    -0.06
    esda
    -0.06
    POSITIVE LOGITS
     اÙĦÙħزÙĬد
    0.11
    æĽ´æ·±åħ¥
    0.11
    åĨįæİ¥åĨįåİī
    0.10
    æľīæĽ´å¤ļ
    0.10
    æĽ´åĬłåĬªåĬĽ
    0.10
     further
    0.10
     ÙħزÙĬد
    0.10
    è¿Ľä¸ĢæŃ¥å®ĮåĸĦ
    0.09
     finer
    0.09
    æľīæĽ´å¤ļçļĦ
    0.09
    Activations Density 0.093%

    No Known Activations