© 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. 12759
    Prev
    Next
    INDEX
    Explanations

    Japanese scholar, philosopher, writer

    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
    обÑĢа
    -0.07
    ung
    -0.07
    razier
    -0.06
    еÑħ
    -0.06
    ka
    -0.06
    ä¸ī个
    -0.06
    anny
    -0.06
    åIJĦçݯèĬĤ
    -0.06
    .lex
    -0.06
     spieg
    -0.06
    POSITIVE LOGITS
    è¿Ļ两ç§į
    0.14
    è¿Ļ两款
    0.14
    两èĢħ
    0.13
    äºĮèĢħ
    0.13
    è¿Ļ两个
    0.13
    è¿Ļ两
    0.13
     beide
    0.12
    ãģ©ãģ¡ãĤīãĤĤ
    0.11
    åīįèĢħ
    0.11
     entrambi
    0.11
    Activations Density 0.422%

    No Known Activations