© 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. 64146
    Prev
    Next
    INDEX
    Explanations

    Josh Stewart

    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
    azi
    -0.07
     McConnell
    -0.07
    vro
    -0.07
    ÑĬл
    -0.06
    çĽijèĢĥ
    -0.06
    impse
    -0.06
     eros
    -0.06
    aque
    -0.06
     Cous
    -0.06
    åĬłç´¢
    -0.06
    POSITIVE LOGITS
    AttributeValue
    0.08
    åĪ
    0.08
    emed
    0.07
    หวัà¸Ļ
    0.07
    ÙĪÙħاÙĨ
    0.07
     Cristi
    0.07
    iola
    0.07
    коми
    0.07
    .yahoo
    0.07
    æķĻèĤ²ç§ijæĬĢæľīéĻIJåħ¬åı¸
    0.07
    Activations Density 0.625%

    No Known Activations