© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30308
    Prev
    Next
    INDEX
    Explanations

    latest, non-American, advanced, play, publishing, segment, different, breast

    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
    éĻĪ家
    -0.07
    æ°´çħ®
    -0.07
    elok
    -0.07
    ĸ
    -0.07
    åıĪ说
    -0.07
    staking
    -0.07
    ember
    -0.06
    apers
    -0.06
     accordingly
    -0.06
    建平
    -0.06
    POSITIVE LOGITS
    éĺħè¯»æľ¬æĸĩåīį
    0.08
    ä½ľæģ¯æŶéĹ´
    0.07
    ä¹Łæĺ¯ä¸ª
    0.07
    iede
    0.07
    _multi
    0.07
    æī©å±ķèµĦæĸĻ
    0.07
    liy
    0.07
    ä¹Łæĺ¯å¾Ī
    0.07
    æħİçĶ¨
    0.07
    ש×Ļ×Ŀ
    0.07
    Activations Density 0.901%

    No Known Activations