© 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. 10652
    Prev
    Next
    INDEX
    Explanations

    -based suffix

    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
    iminal
    -0.09
    agnes
    -0.08
    ç´«éĩij
    -0.08
    наÑĩ
    -0.08
    aggi
    -0.08
    éĶ¦æ¶Ľ
    -0.08
    åį§é¾Ļ
    -0.08
    igné
    -0.08
    à¸ķà¹Į
    -0.08
    èįŁ
    -0.08
    POSITIVE LOGITS
    æµ®äºij
    0.07
    符
    0.07
    -
    0.06
    æ´ª
    0.06
     proxy
    0.06
    ä¼ĺåħĪ
    0.06
    æĮĤéĴ©
    0.06
     proxies
    0.06
    缴è§ĤçļĦæĸ¹å¼ı
    0.06
    维度
    0.06
    Activations Density 0.070%

    No Known Activations