© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14537
    Prev
    Next
    INDEX
    Explanations

    special characters and foreign words

    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
    ä¹īè¯į
    -0.08
    bish
    -0.07
    çĶļèĩ³æĺ¯
    -0.07
    iola
    -0.07
    éĻ¢éĩĮ
    -0.07
     Dall
    -0.07
    Ïĥιά
    -0.07
    å¡ĶçļĦ
    -0.06
    /plain
    -0.06
    aro
    -0.06
    POSITIVE LOGITS
    orman
    0.07
    Dst
    0.06
    ä¸į解
    0.06
    åħ¬çĶ¨
    0.06
    ouz
    0.06
    konom
    0.06
     ìłIJ
    0.06
    _paragraph
    0.06
    åIJĪä½ľ
    0.06
    ihan
    0.06
    Activations Density 0.037%

    No Known Activations