© 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. 2291
    Prev
    Next
    INDEX
    Explanations

    phrase following 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
    åIJĪæł¼åIJİ
    -0.07
    åIJįåŃĹåı«
    -0.06
    uai
    -0.06
    צ×ķ×¢
    -0.06
    åѦçĶŁå¯¹
    -0.06
    åıijæĶ¹
    -0.06
    åIJĪæł¼çİĩ
    -0.06
     Sih
    -0.06
    è¾ħæĸĻ
    -0.06
    ׼×ķת
    -0.06
    POSITIVE LOGITS
    appa
    0.08
    aptive
    0.07
     spokeswoman
    0.07
    奶çĪ¸
    0.07
    asma
    0.07
    æĪijçŃī
    0.07
    æĽ¿
    0.07
    _proxy
    0.07
    ä¸ĩ亿ç¾İåħĥ
    0.07
    opia
    0.06
    Activations Density 0.051%

    No Known Activations