© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 580
    Prev
    Next
    INDEX
    Explanations

    the original

    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
    Negative Logits
    ئÙĦ
    -0.07
    ä¸ĢåĪĩçļĦ
    -0.07
    odge
    -0.07
    éģ¿åħįåĩºçİ°
    -0.06
    è¡Į为åĴĮ
    -0.06
    gnore
    -0.06
    orent
    -0.06
    åĴĮå¿«ä¹IJ
    -0.06
    oids
    -0.06
     Murray
    -0.06
    POSITIVE LOGITS
     ìĤ¬ìļ©ìŀIJê°Ģ
    0.08
    æľīå¿Ĺ
    0.07
    çĶ¨æĪ·
    0.07
    æ±Ĥç¾İ
    0.07
    PrimaryKey
    0.07
    ä¹ĭåīį
    0.07
    UpDown
    0.07
    ombat
    0.07
    YYYY
    0.06
    è¶Ĭä¾Ĩ
    0.06
    Activations Density 0.008%

    No Known Activations