© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33655
    Prev
    Next
    INDEX
    Explanations

    likely adverbs, 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
    ÑĢене
    -0.07
    ç¡®
    -0.07
    chado
    -0.07
    TLS
    -0.07
    è®°ä½ıäºĨ
    -0.07
    ernals
    -0.07
    ordi
    -0.07
    èĢĮä¸Ķè¿ĺæĺ¯
    -0.07
    uby
    -0.07
    mes
    -0.07
    POSITIVE LOGITS
    åIJİèĢħ
    0.08
    ä¹Łè¡Į
    0.08
    è²
    0.07
    LT
    0.07
    éĤ£æł·
    0.07
    ])]
    0.06
    äºĮèĢħ
    0.06
    faq
    0.06
    éĤ£æł·çļĦ
    0.06
    wert
    0.06
    Activations Density 0.019%

    No Known Activations