© 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. 30265
    Prev
    Next
    INDEX
    Explanations

    sadly, unfortunately, more

    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
    æľĢåIJİæĺ¯
    -0.09
    æľĢåIJİåľ¨
    -0.09
    Lastly
    -0.08
    æľĢåIJİä¸Ģ天
    -0.08
    æľĢåIJİçļĦ
    -0.08
     finally
    -0.08
    Finally
    -0.08
    æľĢå¾Įãģ«
    -0.08
    æľĢåIJİè¿ĺæĺ¯
    -0.08
    æľĢåIJİ
    -0.08
    POSITIVE LOGITS
    第ä¸Ģ件äºĭ
    0.07
    cue
    0.06
     owe
    0.06
    heimer
    0.06
    å®ļä½į
    0.06
    é¦ĸåħĪéľĢè¦ģ
    0.06
    leo
    0.06
    doch
    0.06
    åĽŀæĥ³
    0.06
     spite
    0.06
    Activations Density 1.662%

    No Known Activations