© 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. 33072
    Prev
    Next
    INDEX
    Explanations

    conclusions published

    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
    ening
    -0.09
    åħ¢åħ¢ä¸ļä¸ļ
    -0.07
    ificial
    -0.07
    ierce
    -0.07
    robe
    -0.07
    icult
    -0.07
    ä»ĸçªģçĦ¶
    -0.07
    боле
    -0.07
    outine
    -0.06
    eties
    -0.06
    POSITIVE LOGITS
    ì§ĵ
    0.09
    áÅĻ
    0.09
    ož
    0.09
    naires
    0.09
    ÛĮ
    0.09
     ìķĦëĭĮê°Ģ
    0.08
    aires
    0.08
    avanaugh
    0.08
    naire
    0.08
     bahwa
    0.08
    Activations Density 0.007%

    No Known Activations