© 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. 30668
    Prev
    Next
    INDEX
    Explanations

    conditions are met

    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
    egger
    -0.09
    ĥģ
    -0.09
    æĢ»ä¼ļæľī
    -0.09
    andong
    -0.08
    ä¹Łæĺ¯åįģåĪĨ
    -0.08
    ksom
    -0.08
    ä¸ŃéĿĴ
    -0.08
    ontage
    -0.08
    æľ½
    -0.08
    nowrap
    -0.08
    POSITIVE LOGITS
    ä¸Ģæĺ¯
    0.09
    âij
    0.08
    åħ¶ä¸Ģ
    0.08
    ä¸Ģæĺ¯è¦ģ
    0.07
    ;
    0.07
     c
    0.07
    äºĮæĺ¯
    0.07
    able
    0.06
    第ä¸Ģ款
    0.06
    ä¸įæĢķ
    0.06
    Activations Density 0.030%

    No Known Activations