© 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. 39756
    Prev
    Next
    INDEX
    Explanations

    such + noun

    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
    ä¼ĹæīĢåij¨çŁ¥
    -0.09
    ä»ij
    -0.08
    omma
    -0.07
     ám
    -0.07
    çļĦçĶŁçī©
    -0.07
     itself
    -0.07
    agné
    -0.07
    éļħ
    -0.06
    ári
    -0.06
    amac
    -0.06
    POSITIVE LOGITS
    bach
    0.08
    abouts
    0.08
    owers
    0.07
    кеÑĤ
    0.07
    resta
    0.07
    missible
    0.07
    rees
    0.06
    izio
    0.06
    remark
    0.06
    files
    0.06
    Activations Density 0.017%

    No Known Activations