© 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. 18530
    Prev
    Next
    INDEX
    Explanations

    main idea

    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
    jenigen
    -0.09
    ubro
    -0.08
    ãģĦãģĨ
    -0.08
    odata
    -0.08
    plevel
    -0.08
    atro
    -0.08
    FromClass
    -0.08
    kasten
    -0.08
    ormais
    -0.08
    maÃŁen
    -0.08
    POSITIVE LOGITS
    stay
    0.13
    stead
    0.09
    ãĥĨãĥĬãĥ³ãĤ¹
    0.09
    istir
    0.09
    hattan
    0.09
    most
    0.08
    itud
    0.08
    ÃŃsimo
    0.08
    illary
    0.08
    à¹Ĩ
    0.07
    Activations Density 0.048%

    No Known Activations