© 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. 29739
    Prev
    Next
    INDEX
    Explanations

    special characters and non-english 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
    еÑħ
    -0.08
    伦
    -0.07
    ehör
    -0.07
    #echo
    -0.07
    eho
    -0.07
    roll
    -0.07
     hÃł
    -0.07
    tip
    -0.06
     chôm
    -0.06
    exual
    -0.06
    POSITIVE LOGITS
    åĢĴæĺ¯
    0.13
     tampoco
    0.12
    ä¹Łä¸įè¡Į
    0.12
    ä¹Łæ²¡æľī
    0.11
    ä¹Łä¸įåı¯èĥ½
    0.11
    ä¹Łä¸įå¤ļ
    0.10
    ä¹Łä¸į太
    0.10
    ä¹Łæľª
    0.10
     заÑĤо
    0.10
    幸
    0.10
    Activations Density 0.142%

    No Known Activations