© 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. 1389
    Prev
    Next
    INDEX
    Explanations

    Zoilos, algae, Haworthiopsis, Ethyl, Keras, oxygen, creosote, sulfonamides

    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
    çļĦ两个
    -0.07
    宫
    -0.07
    elli
    -0.06
    cher
    -0.06
    ela
    -0.06
    orney
    -0.06
    æľĶ
    -0.06
     allot
    -0.06
    çļĦä¸ī个
    -0.06
    å®®
    -0.06
    POSITIVE LOGITS
    æĪĸåħ¶
    0.11
    (or
    0.11
    oriously
    0.10
    人æĪĸ
    0.10
    esses
    0.09
    å¤įåĪ¶æĪĸ
    0.08
     whichever
    0.08
    ç»ıèIJ¥èĮĥåĽ´åĮħæĭ¬
    0.08
    个æĪĸå¤ļ个
    0.08
    缴æİ¥æĪĸ
    0.08
    Activations Density 0.074%

    No Known Activations