© 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. 56733
    Prev
    Next
    INDEX
    Explanations

    point patterns

    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
    EDIA
    -0.09
    erate
    -0.09
    ованиÑı
    -0.08
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
    ersions
    -0.08
    .mit
    -0.08
    raries
    -0.08
    िता
    -0.08
    keit
    -0.08
    ickness
    -0.08
    POSITIVE LOGITS
    wise
    0.10
    åĦ¿çļĦ
    0.09
     didik
    0.08
    ugal
    0.08
    edly
    0.08
    rophe
    0.08
    ietro
    0.08
    lessly
    0.08
    aneous
    0.08
    ERRUPT
    0.08
    Activations Density 0.083%

    No Known Activations