© 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. 48747
    Prev
    Next
    INDEX
    Explanations

    the more

    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
    Unhandled
    -0.08
    éļıçĿĢæŶéĹ´çļĦæݨ移
    -0.07
    éĴ§
    -0.07
    prit
    -0.07
    ogue
    -0.07
    IDES
    -0.07
    çī¹å°Ķ
    -0.07
     mè
    -0.07
    Elapsed
    -0.07
    ä¸ŃåIJ«æľī
    -0.07
    POSITIVE LOGITS
    ëģĶ
    0.07
    说åIJ§
    0.07
    -called
    0.07
    /from
    0.07
    èĻ½çĦ¶ä»ĸ
    0.06
    (Bundle
    0.06
    ä¸įå¾Ĺä¸į说
    0.06
    éĤ£ä»ĸ
    0.06
     ($(
    0.06
     ÙĪباÙĦ
    0.06
    Activations Density 0.021%

    No Known Activations