© 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. 20817
    Prev
    Next
    INDEX
    Explanations

    one

    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
    ľ
    -0.08
     Dernière
    -0.08
    änen
    -0.08
    æľīæīĢæĢĿ
    -0.08
    ango
    -0.07
    æĦŁåIJĮ
    -0.07
    aré
    -0.07
     letz
    -0.07
     ÙħÙħ
    -0.07
    à§ĭà¦Ĺ
    -0.07
    POSITIVE LOGITS
    å°±å¤ŁäºĨ
    0.11
    æĪĸå°ij
    0.10
    /single
    0.09
     fewer
    0.09
     versus
    0.08
     einzigen
    0.08
    nam
    0.08
     suffice
    0.08
    ìĶ©
    0.08
    åıªæľīä¸Ģ个
    0.08
    Activations Density 0.220%

    No Known Activations