© 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. 31612
    Prev
    Next
    INDEX
    Explanations

    sentence endings 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
    alc
    -0.07
    iato
    -0.07
    ì§ģ
    -0.07
    gau
    -0.07
    omos
    -0.07
    ä¼´ä½ł
    -0.07
    лки
    -0.07
    èºĬ
    -0.07
     Trink
    -0.07
    ocal
    -0.07
    POSITIVE LOGITS
    ensual
    0.08
    esson
    0.07
    øl
    0.07
    马达
    0.07
    ÑĢовÑģкий
    0.07
    åĴĴ
    0.06
    çıŃåŃIJ
    0.06
     pensi
    0.06
    ither
    0.06
    çľĭä¸į
    0.06
    Activations Density 0.012%

    No Known Activations