© 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. 15165
    Prev
    Next
    INDEX
    Explanations

    Chennai to Krasnodar

    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
    ãģĹãģ¾
    -0.07
    agus
    -0.07
    以åīį
    -0.07
    _checked
    -0.06
    èİ«
    -0.06
    à¸Ķà¹īวย
    -0.06
     )
    -0.06
    asa
    -0.06
    çļĦæĸ°é²ľ
    -0.06
     importantly
    -0.05
    POSITIVE LOGITS
    =?,
    0.09
    åİ»åĵªåĦ¿
    0.08
    ä¸Ĭçľĭ
    0.08
     aste
    0.08
    æĦıçļĦ
    0.07
    STALL
    0.07
    ä½ķ为
    0.07
     versus
    0.07
     <->
    0.07
    人ä¸į
    0.07
    Activations Density 0.079%

    No Known Activations