© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17714
    Prev
    Next
    INDEX
    Explanations

    book titles or descriptive phrases

    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
    缸åħ³æݨèįIJ
    -0.10
    æľīä¸ĢåįĬ
    -0.10
     полови
    -0.10
    ÙĪÛĮÛĮ
    -0.09
    رØŃ
    -0.09
    缸åħ³èµĦ讯
    -0.09
    ä¸ĵèIJ¥åºĹ
    -0.09
    åĽłä¸ºè¿Ļ个
    -0.09
    è¿Ļ个åĵģçīĮ
    -0.09
     INFORMA
    -0.09
    POSITIVE LOGITS
    0.07
    .
    0.07
     i
    0.06
    _
    0.06
     armor
    0.06
    1
    0.06
     spec
    0.06
     etc
    0.06
     tyt
    0.06
     th
    0.06
    Activations Density 0.349%

    No Known Activations