© 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. 25554
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    oph
    -0.07
    bre
    -0.07
    enia
    -0.07
    æĬĦ
    -0.07
    yim
    -0.06
    ãĤ¦ãĥĥãĥī
    -0.06
    产
    -0.06
    vet
    -0.06
    éĿ¢åĮħ
    -0.06
    ä¸įå¼Ģ
    -0.06
    POSITIVE LOGITS
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    0.09
    ocities
    0.09
    .SizeType
    0.08
    å·¥ä½ľçļĦå¼Ģå±ķ
    0.08
    ardy
    0.08
    èĪĮå°ĸä¸ĬçļĦ
    0.08
    å¥½å·¥ä½ľ
    0.08
    angent
    0.08
    /www
    0.07
    èĭijå°ıåĮº
    0.07
    Activations Density 0.000%

    No Known Activations