© 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. 44772
    Prev
    Next
    INDEX
    Explanations

    conclusion or final section

    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
    ibro
    -0.07
    ubb
    -0.07
    æŀģåħ¶
    -0.07
    羣æľī
    -0.07
    趣
    -0.07
    ä½ķåħ¶
    -0.06
    ogs
    -0.06
    éĮ
    -0.06
     ثاÙĨÙĬØ©
    -0.06
    è¾Ľ
    -0.06
    POSITIVE LOGITS
    代çłģå¦Ĥä¸ĭ
    0.08
    à¹ģà¸Ķ
    0.07
     prot
    0.07
    åIJĪçIJĨåĮĸ
    0.07
    imary
    0.07
     basically
    0.07
    ted
    0.07
    ikes
    0.07
    cents
    0.07
    æ·¡çĦ¶
    0.07
    Activations Density 0.016%

    No Known Activations