© 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. 26772
    Prev
    Next
    INDEX
    Explanations

    URLs and subject lines

    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
    å¾
    -0.09
    ¬
    -0.07
    attan
    -0.07
    wiki
    -0.07
    åĴ¨è¯¢çĶµè¯Ŀ
    -0.07
    æĭĸçĿĢ
    -0.07
    باء
    -0.06
    ikai
    -0.06
    UIL
    -0.06
    UEL
    -0.06
    POSITIVE LOGITS
    /pay
    0.07
    ç´ł
    0.07
    ä»ĺ
    0.07
    rec
    0.06
    ÑĢна
    0.06
    åħ¬éģĵ
    0.06
    ç´łçļĦ
    0.06
    apkan
    0.06
    æĢĴ
    0.06
    jab
    0.06
    Activations Density 0.001%

    No Known Activations