© 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. 7422
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and protein names

    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
    irs
    -0.08
    ombe
    -0.08
    IRS
    -0.08
    uris
    -0.07
    Mill
    -0.07
     ì²
    -0.07
    åģľè¯¾
    -0.07
    天æĪIJ
    -0.07
    urio
    -0.07
    μαÏĦο
    -0.07
    POSITIVE LOGITS
    Coefficient
    0.07
    ough
    0.07
    æIJı
    0.07
    ounc
    0.06
    ัà¸ģษ
    0.06
    å¥ī
    0.06
    ä½ij
    0.06
    .fig
    0.06
    ÎŃν
    0.06
    å½Ĵ
    0.06
    Activations Density 0.002%

    No Known Activations