© 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. 25328
    Prev
    Next
    INDEX
    Explanations

    walkthrough, recap, explain, details

    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
    ellis
    -0.09
    æľīä¸Ģ份
    -0.08
    ä»»ä½ķå½¢å¼ıçļĦ
    -0.08
    çļĦéĤ£ä¸ª
    -0.07
     famously
    -0.07
    umon
    -0.07
    egt
    -0.07
    ÛĮÙĤ
    -0.07
    enderit
    -0.07
    çļĦéĤ£ä¸ªäºº
    -0.07
    POSITIVE LOGITS
    __:
    0.11
    ä¸Ģä¸ĭ
    0.09
     *:
    0.08
    ï¼ļ
    0.08
    *:
    0.08
    áb
    0.08
    .):
    0.07
    ):
    0.07
    `:
    0.07
    _:
    0.07
    Activations Density 0.004%

    No Known Activations