© 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. 37848
    Prev
    Next
    INDEX
    Explanations

    distinguishing physical or abstract concepts

    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
    ErrorHandler
    -0.09
    à¦Ĥশ
    -0.09
    ÑģовеÑģÑĤ
    -0.09
    å°´
    -0.09
    ubin
    -0.08
    åı°å¤§
    -0.08
    OPY
    -0.08
    èIJ¨æĸ¯
    -0.08
    åį±æľº
    -0.08
    ÑģкаÑĢмли
    -0.08
    POSITIVE LOGITS
    äºĭçī©
    0.08
    æŁIJ个
    0.08
    强è°ĥ
    0.07
    æŃ£åľ¨
    0.07
    ç¾İ好
    0.07
    /
    0.07
    并åĪĹ
    0.07
    æĬĬä¸Ģ个
    0.07
     unspecified
    0.07
    宾è¯Ń
    0.07
    Activations Density 0.022%

    No Known Activations