© 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. 27194
    Prev
    Next
    INDEX
    Explanations

    spatial relationships and properties

    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
    åIJĮ为
    -0.08
    åĩĢåĪ©
    -0.08
    æĭĽ
    -0.07
     volna
    -0.07
    çļĦè¦ģæ±Ĥ
    -0.07
    èĩªè§īæĢ§
    -0.07
    æĹłæĺİæĺ¾
    -0.07
    icter
    -0.07
     ÙĪعدÙħ
    -0.07
    ceaux
    -0.07
    POSITIVE LOGITS
     relationships
    0.09
    relationships
    0.08
     beserta
    0.08
    çŃ
    0.08
    åIJĦ个
    0.08
    æİĴåĪĹ
    0.07
    åľ¨åIJĦ个
    0.07
    åıĺåĮĸæĥħåĨµ
    0.07
    以åıĬåIJĦç§į
    0.07
    åıĬåIJĦ
    0.07
    Activations Density 0.128%

    No Known Activations