© 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. 26235
    Prev
    Next
    INDEX
    Explanations

    parentheses, equals signs, and abbreviations

    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
    tring
    -0.08
     صاØŃ
    -0.07
    ูà¹Ī
    -0.07
    outs
    -0.07
    ÑģÑİ
    -0.07
    fis
    -0.07
     Ausgang
    -0.07
    presso
    -0.07
     {*
    -0.07
    ANCES
    -0.07
    POSITIVE LOGITS
    å¢ŀ
    0.07
    æĨ¬
    0.07
    éĻ¡
    0.06
     Increment
    0.06
     change
    0.06
    èĪĪ
    0.06
    Increment
    0.06
    erializer
    0.06
    slope
    0.06
    åı®
    0.06
    Activations Density 0.009%

    No Known Activations