© 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. 40901
    Prev
    Next
    INDEX
    Explanations

    And followed by conjunction or pronoun

    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
    opher
    -0.08
    äºļäºİ
    -0.07
    ÙĬ
    -0.07
    åį´æĺ¯
    -0.07
    weise
    -0.07
    nai
    -0.07
    addy
    -0.07
    iasco
    -0.07
    åĽ¾æºIJ
    -0.06
    ãģ¾ãģļ
    -0.06
    POSITIVE LOGITS
     ëĤĺìĦľ
    0.12
    oret
    0.09
    ż
    0.09
    åıįè¿ĩæĿ¥
    0.09
    rey
    0.08
    è¯Ŀ说
    0.08
    urance
    0.08
    /OR
    0.08
    fter
    0.07
    że
    0.07
    Activations Density 0.088%

    No Known Activations