© 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. 26402
    Prev
    Next
    INDEX
    Explanations

    introductions

    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
    人åİ»
    -0.08
    ç²¾ç¥ŀçļĦ
    -0.07
    æĪIJä¸Ģ
    -0.07
    anic
    -0.07
    arnings
    -0.07
    表çİ°äºĨ
    -0.07
    å¾®åºĹ
    -0.07
    ivu
    -0.07
    å°¤
    -0.07
    çļĦéĩį
    -0.07
    POSITIVE LOGITS
    èĩªæĪijä»ĭç»į
    0.12
     surname
    0.11
    å§ĵ
    0.10
    ä»ĭç»įä¸Ģä¸ĭ
    0.10
    æĪijåı«
    0.10
    èĩªç§°
    0.10
     name
    0.09
    ç»Ļ大家ä»ĭç»į
    0.09
     identity
    0.08
    大åIJį
    0.08
    Activations Density 0.211%

    No Known Activations