© 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. 31048
    Prev
    Next
    INDEX
    Explanations

    special characters and code formatting

    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
    eru
    -0.10
    зади
    -0.10
    à§įস
    -0.10
    à§įত
    -0.10
    er
    -0.10
    erii
    -0.10
    erio
    -0.09
    à§įন
    -0.09
    rody
    -0.09
    colas
    -0.09
    POSITIVE LOGITS
    able
    0.09
    ÑģÑı
    0.09
    ©
    0.09
    ¨
    0.09
    nya
    0.08
    t
    0.07
    c
    0.07
    ven
    0.07
    äºĨ对
    0.07
    iet
    0.07
    Activations Density 0.011%

    No Known Activations