© 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. 29895
    Prev
    Next
    INDEX
    Explanations

    cosmic or cosmology

    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
    Åijl
    -0.08
    edly
    -0.08
    /dis
    -0.07
    رج
    -0.07
    (li
    -0.07
     subparagraph
    -0.07
    trand
    -0.07
    æĪĸ缺
    -0.07
     possesso
    -0.06
    psilon
    -0.06
    POSITIVE LOGITS
    ation
    0.10
    wide
    0.09
    opolitan
    0.09
    à¸Īร
    0.08
    -wide
    0.08
    ically
    0.08
    æĢ§åľ°
    0.08
    баÑĤ
    0.07
    ’Brien
    0.07
    å°¼äºļ
    0.07
    Activations Density 0.013%

    No Known Activations