© 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. 13093
    Prev
    Next
    INDEX
    Explanations

    found to

    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
    hoven
    -0.08
    áĥIJáĥ®
    -0.07
    icut
    -0.07
    ARTA
    -0.07
    hini
    -0.07
    åĪ«å¿ĺäºĨ
    -0.07
    .tpl
    -0.07
    بÙĪر
    -0.07
    beck
    -0.07
    人ãģ¨
    -0.07
    POSITIVE LOGITS
    °
    0.08
     olev
    0.08
    åħ·æľīçļĦ
    0.08
    erweise
    0.08
     être
    0.07
     داراÛĮ
    0.07
    edly
    0.07
    PUTE
    0.07
    spinner
    0.07
     avoir
    0.07
    Activations Density 0.498%

    No Known Activations