© 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. 27678
    Prev
    Next
    INDEX
    Explanations

    basis for

    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
    .au
    -0.08
    abouts
    -0.08
    ä½ľåĪĻ
    -0.08
    تا
    -0.08
    ترا
    -0.08
    itudes
    -0.07
    egrity
    -0.07
    ansas
    -0.07
    onan
    -0.07
    ابع
    -0.07
    POSITIVE LOGITS
    ãģĺãĤģãģ¦
    0.11
    lide
    0.07
    -independent
    0.07
    kampf
    0.07
    ÙĬت
    0.07
    ÙĬ
    0.07
    à¸ķà¹Į
    0.07
    iog
    0.07
    àµįà´¯
    0.07
    ForResult
    0.07
    Activations Density 0.012%

    No Known Activations