© 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. 10138
    Prev
    Next
    INDEX
    Explanations

    type, produce, yielded, resultant

    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
    æ¯ı人
    -0.08
    ç¼ĵ
    -0.07
    èݱ德
    -0.07
    æıIJçĤ¼
    -0.07
     disag
    -0.07
    å°ıæľī
    -0.07
    举éģĵ
    -0.07
    æ³Ľ
    -0.07
    èijĨ
    -0.06
     stim
    -0.06
    POSITIVE LOGITS
    aight
    0.08
    uong
    0.08
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.08
    éķľ
    0.07
    andler
    0.07
    ucker
    0.07
     resultant
    0.07
     upright
    0.07
    ä¸įè´¥
    0.07
     overturn
    0.07
    Activations Density 0.001%

    No Known Activations