© 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. 63495
    Prev
    Next
    INDEX
    Explanations

    external sources or locations

    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
     StatusCode
    -0.08
     LAT
    -0.07
    Advice
    -0.07
    ophobic
    -0.07
    bots
    -0.07
    accord
    -0.07
    åĶ®åĩº
    -0.07
    羡
    -0.07
    æĢĿæĥ³ä¸Ĭ
    -0.06
    çļĦ大äºĭ
    -0.06
    POSITIVE LOGITS
    å¤ĸéĥ¨
    0.11
     external
    0.10
     sources
    0.09
     Source
    0.09
     source
    0.09
     externa
    0.09
     External
    0.09
    æºIJ
    0.09
    external
    0.09
     Sources
    0.09
    Activations Density 0.502%

    No Known Activations