© 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. 21203
    Prev
    Next
    INDEX
    Explanations

    diamagnetism

    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
    ä¸į对称
    -0.08
    à¤ĸा
    -0.07
    类似çļĦ
    -0.07
    acher
    -0.07
    à¨ĸ
    -0.07
    æ´¾åıij
    -0.07
    SC
    -0.07
    è¿Ľè¡Įæµĭè¯ķ
    -0.07
     asymmetric
    -0.06
    à¤ĸ
    -0.06
    POSITIVE LOGITS
    åĪļ好
    0.11
    æģ°å¥½
    0.10
    æŃ£å¥½
    0.09
    ãģ¡ãĤĩãģĨãģ©
    0.08
    åĪļåĪļ好
    0.08
    FullPath
    0.08
    åīĽå¥½
    0.08
    æģ°å·§
    0.07
     saturated
    0.07
    已满
    0.07
    Activations Density 0.010%

    No Known Activations