© 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. 25639
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
    -flag
    -0.07
    æķĻèĤ²ä¸Ńå¿ĥ
    -0.06
    antt
    -0.06
    çļĪ
    -0.06
    eed
    -0.06
    nud
    -0.06
    é¦ĸæ¬¡åľ¨
    -0.06
    é¦Ħ饨
    -0.06
    åĢ¼ä¸º
    -0.06
    embedding
    -0.06
    POSITIVE LOGITS
    aping
    0.07
    å½¢å¼ıçļĦ
    0.07
    èį·åĮħ
    0.07
     higien
    0.07
    å±ħæĺĵ
    0.07
    à¹Ģสมà¸Ń
    0.07
    积
    0.07
    eterminate
    0.07
    á»ĭa
    0.07
    lander
    0.07
    Activations Density 0.010%

    No Known Activations