© 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. 50779
    Prev
    Next
    INDEX
    Explanations

    updates in your inbox

    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
     perv
    -0.06
     s
    -0.06
    åĪ«æľī
    -0.06
    æī©å±ķèµĦæĸĻ
    -0.06
     perme
    -0.06
     https
    -0.06
     con
    -0.06
    åīij
    -0.06
    ä¹ħè¿ľ
    -0.06
    lop
    -0.06
    POSITIVE LOGITS
    AndGet
    0.08
    readcrumb
    0.08
    ãģ®è²©
    0.08
     Ðķги
    0.08
    iedo
    0.07
    SingleNode
    0.07
    пи
    0.07
     rigu
    0.07
    éķ¿æĮīè¯ĨåĪ«äºĮç»´çłģ
    0.07
    enstr
    0.07
    Activations Density 1.025%

    No Known Activations