© 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. 20184
    Prev
    Next
    INDEX
    Explanations

    invariant transformations and 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
    æīĵèµ·
    -0.08
    à§įত
    -0.08
    anken
    -0.08
    MEA
    -0.08
    inous
    -0.08
    åIJIJåĩº
    -0.08
    åĪ«æł·
    -0.08
    £¼
    -0.08
    ersatz
    -0.07
     اÙĦÙĦا
    -0.07
    POSITIVE LOGITS
     fixing
    0.08
    æ´ĭ
    0.07
     equivalence
    0.07
     rog
    0.07
     resh
    0.07
     permutation
    0.07
    åIJĮ
    0.07
     preserving
    0.07
    éľ
    0.06
    强
    0.06
    Activations Density 0.011%

    No Known Activations