© 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. 63290
    Prev
    Next
    INDEX
    Explanations

    special characters after numbers

    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
    ÛĮات
    -0.09
    iset
    -0.09
    à¹Ĩ
    -0.08
    uah
    -0.08
    ovac
    -0.08
    uari
    -0.08
    niu
    -0.08
    uj
    -0.08
    ede
    -0.08
    eme
    -0.08
    POSITIVE LOGITS
    /her
    0.09
    erven
    0.08
    uddin
    0.06
    åĺĪ
    0.06
    '
    0.06
    's
    0.06
    metros
    0.06
    artz
    0.06
    æ³Ĺ
    0.06
    åĴĮ第äºĮ
    0.06
    Activations Density 0.026%

    No Known Activations