© 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. 15514
    Prev
    Next
    INDEX
    Explanations

    rockles

    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
    ereo
    -0.08
    èĴ¸èĴ¸æĹ¥ä¸Ĭ
    -0.07
    kl
    -0.07
    åij½çļĦ
    -0.07
    eldon
    -0.07
    奴婢
    -0.07
    åķĨä¸ļçī¹è®¸ç»ıèIJ¥
    -0.07
    ä¸įæĦģ
    -0.07
    ä»İè½»
    -0.07
    æ®·åĪĩ
    -0.07
    POSITIVE LOGITS
    两é¢Ĺ
    0.08
    两年æĿ¥
    0.07
    rovers
    0.07
    æĺ¯ä¸Ģé¢Ĺ
    0.07
     yay
    0.07
    ship
    0.06
    å¥ĩçī¹çļĦ
    0.06
    çĤ®å¼¹
    0.06
    ijn
    0.06
    perse
    0.06
    Activations Density 0.033%

    No Known Activations