© 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. 9504
    Prev
    Next
    INDEX
    Explanations

    powerful positive adjectives

    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
    ìĥī
    -0.08
    å¯ĨåĪĩæݥ触
    -0.08
    å¤§ä¾ł
    -0.08
    大礼
    -0.08
    è«®
    -0.08
    Äįka
    -0.07
    icional
    -0.07
    idar
    -0.07
    ilver
    -0.07
    abel
    -0.07
    POSITIVE LOGITS
    强大çļĦ
    0.13
     mẽ
    0.12
    强大
    0.12
     powerful
    0.12
     mạnh
    0.12
     puiss
    0.11
    æľīåĬĽçļĦ
    0.11
    åIJİçĽ¾
    0.11
    æľĢ强çļĦ
    0.11
    æľīåĬĽ
    0.11
    Activations Density 0.104%

    No Known Activations