© 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. 24781
    Prev
    Next
    INDEX
    Explanations

    life and its contexts

    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
    WARD
    -0.08
    abouts
    -0.08
    sembly
    -0.07
    -fashioned
    -0.07
    ymar
    -0.07
    ork
    -0.07
    gether
    -0.07
    edt
    -0.07
    ếm
    -0.07
     prej
    -0.07
    POSITIVE LOGITS
    ively
    0.09
    pras
    0.08
    à¸į
    0.08
    ilde
    0.08
    åıªæľīä¸Ģ次
    0.08
    ä½ĵå¾ģ
    0.07
    egrity
    0.07
     halnya
    0.07
    -être
    0.07
    à¥įरà¥ĭ
    0.07
    Activations Density 0.001%

    No Known Activations