© 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. 2136
    Prev
    Next
    INDEX
    Explanations

    phenomenon

    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
    á»ıi
    -0.09
    ä¸Ĭè·¯
    -0.08
    ÙĪÙĬÙĦ
    -0.08
    ãĥŃãĥŀ
    -0.08
    注åĨĮæĪIJç«ĭ
    -0.08
    羣æŃ£æĪIJ为
    -0.08
    éĺ¿åį¡
    -0.07
    ÙĪÙĦÙĩ
    -0.07
    åĢ¾åĬĽ
    -0.07
    пил
    -0.07
    POSITIVE LOGITS
    åĵ²çIJĨ
    0.11
    ä½ĵçİ°
    0.10
    ä½ĵçİ°äºĨ
    0.09
    çݰ象
    0.09
     phenomenon
    0.08
    è¿IJçĶ¨äºĨ
    0.07
    å®ŀä¾ĭ
    0.07
    çı¾è±¡
    0.07
    ä½ĵçİ°åĩº
    0.07
    åİŁçIJĨ
    0.07
    Activations Density 0.012%

    No Known Activations