© 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. 42372
    Prev
    Next
    INDEX
    Explanations

    directory paths and software modules

    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
    à¹Ģà¸Ĭิà¸ĩ
    -0.09
    ain
    -0.08
    prud
    -0.07
    bec
    -0.07
    /password
    -0.07
    ibbon
    -0.07
    ÑĨенÑĤÑĢ
    -0.07
    对å¤ĸ
    -0.07
    ardon
    -0.07
    ipi
    -0.07
    POSITIVE LOGITS
    uxtap
    0.08
    ļ
    0.07
     arras
    0.07
    tical
    0.07
    enic
    0.07
    usch
    0.07
    zing
    0.07
    amana
    0.07
    eiro
    0.06
    sider
    0.06
    Activations Density 0.010%

    No Known Activations