© 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. 64747
    Prev
    Next
    INDEX
    Explanations

    rising, falling, quadratic, symmetry

    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
    _MUT
    -0.08
    ecker
    -0.07
    串串
    -0.07
    ä¸įç»Ŀ
    -0.07
    æķŀ
    -0.07
    .Layer
    -0.07
    åħ¨æł¡å¸ĪçĶŁ
    -0.07
    inton
    -0.07
    ava
    -0.07
    =open
    -0.07
    POSITIVE LOGITS
    转æĬĺçĤ¹
    0.09
     Sym
    0.08
    Sym
    0.08
    åıįå¼¹
    0.08
    æİī头
    0.08
     symmetry
    0.08
    sym
    0.08
    åĽŀèIJ½
    0.08
    åĽŀåįĩ
    0.08
    æĭIJçĤ¹
    0.08
    Activations Density 0.022%

    No Known Activations