© 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. 1170
    Prev
    Next
    INDEX
    Explanations

    rights reserved; copyright notices

    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
     scratch
    -0.07
    纶
    -0.07
    ä¹ĭæīĢ以
    -0.06
     ‘’
    -0.06
     b
    -0.06
    wein
    -0.06
    ber
    -0.06
    鼷
    -0.06
    lise
    -0.06
     w
    -0.06
    POSITIVE LOGITS
    çļĦæľĭåıĭåı¯ä»¥
    0.09
    æĹ¥åĪ¶
    0.08
    èį·åĮħ
    0.08
    preferred
    0.08
    è¿ŀäºij
    0.08
    ä¹ħä¹ĭ
    0.07
    åı¯æ¢¦
    0.07
    pell
    0.07
    ä¹ħèĢĮ
    0.07
    æĩĤçļĦ
    0.07
    Activations Density 0.003%

    No Known Activations