© 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. 2709
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    iod
    -0.07
    人çļĦçĶŁåij½
    -0.06
     div
    -0.06
    åģļéĶĻ
    -0.06
    _pull
    -0.06
    æįº
    -0.06
    æĺĮ
    -0.06
     fav
    -0.06
    èĽĨ
    -0.06
    åģļ强
    -0.06
    POSITIVE LOGITS
    eve
    0.09
     stille
    0.08
    æįİ
    0.07
    ofile
    0.07
    Åijség
    0.07
    áĥ¦
    0.07
    sky
    0.07
    è·ĥ
    0.07
    slash
    0.07
    åĿł
    0.07
    Activations Density 0.052%

    No Known Activations