© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64214
    Prev
    Next
    INDEX
    Explanations

    empty list/set/string/graph/objects

    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
    ä½İå»ī
    -0.07
    ierz
    -0.06
    niest
    -0.06
    manship
    -0.06
    注æĦıçļĦæĺ¯
    -0.06
    ä½İäºĨ
    -0.06
     overs
    -0.06
     пони
    -0.06
    xF
    -0.06
    down
    -0.06
    POSITIVE LOGITS
    æĪĸå°ij
    0.09
    .empty
    0.08
    agg
    0.08
    空çļĦ
    0.08
    空
    0.08
    æĪĸèĢħæľī
    0.08
    æĪĸæľª
    0.07
    asket
    0.07
    (empty
    0.07
    ihak
    0.07
    Activations Density 0.017%

    No Known Activations