© 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. 17011
    Prev
    Next
    INDEX
    Explanations

    permanent | temporary

    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
    交æ±ĩ
    -0.07
    è¿Ŀ
    -0.07
     ajud
    -0.07
     aide
    -0.07
    åĴĮåİ¿
    -0.07
    转贴
    -0.07
    èĩªå¹¼
    -0.07
    å·´åĭĴ
    -0.07
    Extras
    -0.07
    orce
    -0.07
    POSITIVE LOGITS
    æ°¸ä¹ħæĢ§
    0.11
     Permanent
    0.11
     permanent
    0.10
     permanently
    0.10
    æ°¸ä¹ħ
    0.10
    Permanent
    0.10
     Perman
    0.09
    permanent
    0.09
     temporary
    0.09
     temporarily
    0.08
    Activations Density 0.100%

    No Known Activations