© 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. 19225
    Prev
    Next
    INDEX
    Explanations

    date, name, or numeric sequence

    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
    æķ°çĻ¾
    -0.08
    æѤåīįçļĦ
    -0.08
     offenbar
    -0.07
     dozens
    -0.07
    ä½łåı¯èĥ½
    -0.07
    æķ°åįģ
    -0.07
    idar
    -0.07
    æѤåīį
    -0.07
    ãĤ¯ãĥ«ãĥŀ
    -0.07
    è¿Ħä»Ĭ
    -0.07
    POSITIVE LOGITS
    æµħæŀIJ
    0.10
    æµħè°Ī
    0.10
    éĢļè¿ĩæŃ¤æ¬¡
    0.09
     researched
    0.08
     Firstly
    0.08
     Conclus
    0.08
    éĢļè¿ĩæľ¬æ¬¡
    0.08
    å¦Ĥèĭ¥
    0.08
    åĪĨæŀIJåıĬ
    0.07
    å·¥åķĨè¡ĮæĶ¿ç®¡çIJĨå±Ģ
    0.07
    Activations Density 1.019%

    No Known Activations