© 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. 1555
    Prev
    Next
    INDEX
    Explanations

    git commands or code constructs

    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
    æĢª
    -0.07
    NIC
    -0.06
    Deal
    -0.06
    obe
    -0.06
    æį®
    -0.06
    eroy
    -0.06
    大éĢļ
    -0.06
    ¦
    -0.06
    ç®Ģä»ĭ
    -0.06
    kest
    -0.06
    POSITIVE LOGITS
    ä¸İä¹ĭ
    0.11
    åħ¶ä»ĸ
    0.10
    (other
    0.10
    çļĦåħ¶ä»ĸ
    0.10
     other
    0.10
    other
    0.10
     thereof
    0.09
    åĪ¥çļĦ
    0.09
    对å®ĥ
    0.09
    对åħ¶è¿Ľè¡Į
    0.09
    Activations Density 0.191%

    No Known Activations