© 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. 17466
    Prev
    Next
    INDEX
    Explanations

    question marks and punctuation

    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
    ×IJר
    -0.08
    anco
    -0.08
    彪
    -0.07
    onsel
    -0.07
    inan
    -0.07
    lang
    -0.07
    kul
    -0.07
     непÑĢавилÑĮ
    -0.07
    åį¡æĸ¯
    -0.07
    oupon
    -0.06
    POSITIVE LOGITS
    æĢİä¹ĪåĬŀ
    0.10
    æĢİä¹ĪåĬŀåij¢
    0.10
    解åĨ³åĬŀæ³ķ
    0.09
    解åĨ³æĸ¹æ³ķ
    0.09
    å¥½åľ¨
    0.08
    æĢİ麼辦
    0.08
    解åĨ³æĸ¹æ¡Ī
    0.07
    åı¯éĩĩçĶ¨
    0.07
    JOR
    0.07
    è°ĥæķ´ä¸º
    0.07
    Activations Density 0.126%

    No Known Activations