© 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. 56393
    Prev
    Next
    INDEX
    Explanations

    Purge, purges, purges

    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
    éĢĽè¡Ĺ
    -0.08
    绽
    -0.07
     Catan
    -0.07
     fair
    -0.07
    ä¸įæ¼ı
    -0.07
    被æĴŀ
    -0.07
    ä»İ容
    -0.06
     Fair
    -0.06
     taxable
    -0.06
    åĴĮèī¯å¥½çļĦ
    -0.06
    POSITIVE LOGITS
    çļĦéĶĻ误
    0.09
    æŀģ端
    0.09
    éĶĻ误çļĦ
    0.08
    leveland
    0.08
     ÑĢежим
    0.08
    纯æ´ģ
    0.08
    éĶĻ误
    0.08
    .widgets
    0.07
    迫害
    0.07
    FileStream
    0.07
    Activations Density 0.008%

    No Known Activations