© 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. 20279
    Prev
    Next
    INDEX
    Explanations

    Einstein manifolds or flux

    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
    婧
    -0.07
    omon
    -0.07
    æijĩ
    -0.07
    æĴ¬
    -0.07
    heb
    -0.07
    umon
    -0.07
     Halb
    -0.07
    éĩī
    -0.07
    ½
    -0.07
    aval
    -0.07
    POSITIVE LOGITS
    æµģåĬ¨
    0.09
     flowing
    0.08
     Murray
    0.07
    éĺŁ
    0.07
     flow
    0.07
    æµģåĬ¨çļĦ
    0.07
    å¿į
    0.07
     flows
    0.07
    æĴŃ
    0.07
     Pur
    0.07
    Activations Density 0.002%

    No Known Activations