© 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. 25216
    Prev
    Next
    INDEX
    Explanations

    isotopes or chemical compounds

    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
    è¿ĩ好
    -0.07
    èĩŃåij³
    -0.07
    åįĬçĤ¹
    -0.07
    è¿ĩä¸Ĭ
    -0.06
     isi
    -0.06
    ä¼ļåıĺ
    -0.06
    æĥŃ
    -0.06
    çļĦæ²Ļ
    -0.06
    igo
    -0.06
    à¹Ĩ
    -0.06
    POSITIVE LOGITS
    ĥĿ
    0.08
    <|box_end|>
    0.08
    üst
    0.08
    atina
    0.08
    istian
    0.07
    Outlined
    0.07
    0.07
    ĵĺ
    0.07
    åĴĮ丰å¯ĮçļĦ
    0.07
    gable
    0.07
    Activations Density 0.021%

    No Known Activations