© 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. 3929
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
    iddle
    -0.07
    à®°à®ļ
    -0.07
    оÑĢÑĤи
    -0.07
     Zahl
    -0.06
    arium
    -0.06
    ara
    -0.06
    illa
    -0.06
    azu
    -0.06
    alez
    -0.06
    accio
    -0.06
    POSITIVE LOGITS
     à¹Ĩ
    0.08
    ï¸ı
    0.08
    æł¸éħ¸æ£Ģæµĭéĺ´æĢ§
    0.08
    stens
    0.08
    -legged
    0.07
    ÙĪÙ¾
    0.07
    heit
    0.07
    -way
    0.07
    ards
    0.06
    pth
    0.06
    Activations Density 0.781%

    No Known Activations