© 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. 20480
    Prev
    Next
    INDEX
    Explanations

    mathematical indices and expressions

    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
     itself
    -0.08
    en
    -0.08
    -hooks
    -0.07
    aggio
    -0.07
    ow
    -0.07
    åIJĦåİ¿
    -0.06
    两侧
    -0.06
     Hash
    -0.06
    ake
    -0.06
    abant
    -0.06
    POSITIVE LOGITS
    ouz
    0.07
    idla
    0.07
    约èĢĮåIJĮ
    0.07
    年建
    0.07
    年建éĢł
    0.07
    ÏĥÏĦή
    0.07
    vore
    0.07
    icular
    0.07
    微信æī«çłģ
    0.07
    imens
    0.07
    Activations Density 0.004%

    No Known Activations