© 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. 23749
    Prev
    Next
    INDEX
    Explanations

    table separators and headers

    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
    илÑĮ
    -0.09
    leigh
    -0.09
    idis
    -0.08
    infeld
    -0.08
    zelt
    -0.08
    iewicz
    -0.08
    ijski
    -0.08
    ypsum
    -0.08
    åĿŀ
    -0.08
    зли
    -0.08
    POSITIVE LOGITS
    anto
    0.07
    çĶŁçļĦ
    0.07
    anje
    0.07
    agner
    0.06
     tal
    0.06
    0.06
    ģ
    0.06
    Å©
    0.06
    ound
    0.06
     interd
    0.06
    Activations Density 0.002%

    No Known Activations