© 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. 37955
    Prev
    Next
    INDEX
    Explanations

    similar to other cities

    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
    rauch
    -0.07
    _eg
    -0.07
    å·²è¿ŀç»Ń
    -0.07
     McMaster
    -0.07
     Roos
    -0.06
    åģıåģı
    -0.06
    æĢ§åij½
    -0.06
     اÙĦÙĦ
    -0.06
    å·²ç»ıè¿ŀç»Ń
    -0.06
    дика
    -0.06
    POSITIVE LOGITS
    类似çļĦ
    0.17
     similarly
    0.17
     similar
    0.17
    similar
    0.14
    类似
    0.14
     ÙħشابÙĩ
    0.14
    çĽ¸ä¼¼çļĦ
    0.14
     serupa
    0.13
    类似éĹ®é¢ĺ
    0.13
     ähnliche
    0.13
    Activations Density 0.291%

    No Known Activations