© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42484
    Prev
    Next
    INDEX
    Explanations

    numbers followed by ordinal suffixes

    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
    æ»ĵ
    -0.09
    (/^\
    -0.09
    èĢ¿èĢ¿
    -0.08
    änn
    -0.08
    èĭ¦è¾£
    -0.08
    à»ģ
    -0.07
    omnia
    -0.07
    szcz
    -0.07
    terne
    -0.07
    ../
    -0.07
    POSITIVE LOGITS
    ↵↵    ↵
    0.07
    use
    0.06
    à¸ģิà¸Īà¸ģาร
    0.06
    ipan
    0.06
     applied
    0.06
    ï¼ij
    0.06
    ician
    0.06
     Blan
    0.06
    iche
    0.06
    riel
    0.06
    Activations Density 0.001%

    No Known Activations