© 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. 8518
    Prev
    Next
    INDEX
    Explanations

    mechanical and anical terms

    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
    iente
    -0.09
    ting
    -0.07
    gether
    -0.07
    ogh
    -0.07
    -reaching
    -0.07
    enser
    -0.07
    ehme
    -0.07
    à¹Ģà¸Ĺียม
    -0.07
    ential
    -0.07
    obet
    -0.07
    POSITIVE LOGITS
    anical
    0.09
    å·¥ä¸ļåĩºçīĪ社
    0.09
    hattan
    0.09
    ضÙĬ
    0.09
    intosh
    0.09
    «
    0.08
    stück
    0.08
    /material
    0.08
    licity
    0.08
    Ø©
    0.08
    Activations Density 0.019%

    No Known Activations