© 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. 34086
    Prev
    Next
    INDEX
    Explanations

    esterification, integration, fusion, splicing, DNA, RNA

    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
    éĩĩ
    -0.08
    äºĨ解çļĦ
    -0.06
    ply
    -0.06
    illery
    -0.06
    ÃŃž
    -0.06
    çº¢é¢ľ
    -0.06
    éĩ
    -0.06
    åĵģ
    -0.06
    ä¹ł
    -0.06
    lern
    -0.06
    POSITIVE LOGITS
    ragment
    0.08
     unlink
    0.08
    LEASE
    0.07
    oves
    0.07
    arton
    0.07
    两段
    0.07
     precondition
    0.07
     splice
    0.07
     DNA
    0.07
    éĶļ
    0.07
    Activations Density 0.027%

    No Known Activations