© 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. 10566
    Prev
    Next
    INDEX
    Explanations

    medical and scientific analysis

    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
    liness
    -0.09
    ths
    -0.09
    ality
    -0.08
    nisse
    -0.08
    -ever
    -0.08
    еÑĩ
    -0.08
    alités
    -0.07
    smith
    -0.07
    sWith
    -0.07
    nalité
    -0.07
    POSITIVE LOGITS
    گرÛĮ
    0.11
    گراÙĨ
    0.10
    तà¥įम
    0.10
    åħ¥å¾®
    0.09
    IGNAL
    0.09
    /testing
    0.08
    éĢıå½»
    0.08
    گر
    0.08
    imony
    0.08
    neh
    0.08
    Activations Density 0.076%

    No Known Activations