© 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. 10830
    Prev
    Next
    INDEX
    Explanations

    structurally, numerically, surgically, prospectively

    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
    sWith
    -0.09
    缸è¾ħ缸æĪIJ
    -0.08
    ç´¢æĢ§
    -0.08
    ãģ³
    -0.08
    ÑģÑı
    -0.08
    çļĦ
    -0.07
    anes
    -0.07
    ä¸įåĢĴ
    -0.07
     noqa
    -0.07
    åŃ¦ä»¥èĩ´çĶ¨
    -0.07
    POSITIVE LOGITS
    ically
    0.18
    ally
    0.18
    ly
    0.17
    ively
    0.14
    ously
    0.14
    mente
    0.13
    ently
    0.13
    arily
    0.12
    ually
    0.12
    ìłģìľ¼ë¡ľ
    0.12
    Activations Density 0.119%

    No Known Activations