© 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. 26530
    Prev
    Next
    INDEX
    Explanations

    respectively, ex, iii, Wind, type, wells

    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
    arca
    -0.07
    avy
    -0.06
    è¬Ŀ
    -0.06
    .sys
    -0.06
    alex
    -0.06
    lina
    -0.06
    å¤ļåIJĥ
    -0.06
    çĪ¶å¥³
    -0.06
    agar
    -0.06
    Convertible
    -0.06
    POSITIVE LOGITS
    ä¹ŁæĬĬ
    0.08
    ihar
    0.08
    irected
    0.08
    缸继
    0.07
    åij½åIJį为
    0.07
    éĵ¿
    0.07
     respective
    0.07
     ì°¨ë¡Ģ
    0.07
    ÙħÙĪÙĦØ©
    0.07
    bek
    0.07
    Activations Density 0.002%

    No Known Activations