© 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. 20993
    Prev
    Next
    INDEX
    Explanations

    make sure to [verb]

    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
     simply
    -0.08
    oret
    -0.08
    ä½ķå¿ħ
    -0.07
    ä¸ĢèĪ¬çļĦ
    -0.07
     simplesmente
    -0.07
    æĺ¯åIJ¦åŃĺåľ¨
    -0.07
     certes
    -0.07
     semplicemente
    -0.07
     frankly
    -0.06
    ợ
    -0.06
    POSITIVE LOGITS
    ä¸įæĺ¯åľ¨
    0.09
    ãģĹãĤĤ
    0.08
    åħ¬å¹³åħ¬æŃ£
    0.08
    ä¸įæĺ¯ä»Ģä¹Ī
    0.08
    ä¸įä¼ļåĽłä¸º
    0.08
    ä¸įè¦ģçĶ¨
    0.08
     везде
    0.08
    ä¸įè¦ģéĶĻè¿ĩ
    0.08
    ä¸įæĺ¯åĽłä¸º
    0.08
    phine
    0.08
    Activations Density 0.012%

    No Known Activations