© 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. 30537
    Prev
    Next
    INDEX
    Explanations

    ordering or ranking items

    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
    ead
    -0.08
    æµ·ä¸ľ
    -0.08
    æĪ¿åĨħ
    -0.08
     ÐŁÑĢоÑģмоÑĤÑĢов
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    åĿĬ
    -0.07
    è¡Įäºij
    -0.07
     пеÑĢео
    -0.07
    åĬłåħ¥æĶ¶èĹı
    -0.07
    odka
    -0.07
    POSITIVE LOGITS
    éĢīæĭ©åľ¨
    0.10
    ä¸ŃéĢīæĭ©
    0.10
    éĢīæĭ©ä¸į
    0.09
    ä¸ŃæľĢ
    0.09
    éĢīæĭ©
    0.09
    æĮijéĢī
    0.08
    åħ¶ä¸ŃæľĢ
    0.08
    ä¼ļéĢīæĭ©
    0.08
    åºĶéĢīæĭ©
    0.08
    éģ¸æĵĩ
    0.08
    Activations Density 0.071%

    No Known Activations