© 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. 2060
    Prev
    Next
    INDEX
    Explanations

    chimes and ringing

    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
    asis
    -0.08
    æĮ¨
    -0.06
     defy
    -0.06
    å¾Ģå¤į
    -0.06
    plication
    -0.06
     Days
    -0.06
    æĪĸå°ij
    -0.06
    åħ°å¾·
    -0.06
    æ¯Ĥ
    -0.06
    çķħæīĢ欲è¨Ģ
    -0.06
    POSITIVE LOGITS
    åĤ¬ä¿ĥ
    0.11
    ä¸įæĹ©
    0.10
    示æĦı
    0.09
    åĪ¶æŃ¢
    0.09
    赶紧
    0.09
    rompt
    0.09
    åĤ¬
    0.09
    æĪij赶紧
    0.08
     lest
    0.08
    åĽŀè¿ĩç¥ŀæĿ¥
    0.08
    Activations Density 0.085%

    No Known Activations