© 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. 2089
    Prev
    Next
    INDEX
    Explanations

    assume that

    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
     certainly
    -0.09
     presumably
    -0.09
     reportedly
    -0.08
     often
    -0.08
     typically
    -0.07
    éĢļ常
    -0.07
     hopefully
    -0.07
    åģĩå¦Ĥ
    -0.07
    ä¸ĢèĪ¬éĥ½ä¼ļ
    -0.07
    éĿŀ
    -0.07
    POSITIVE LOGITS
    енÑģи
    0.08
     somehow
    0.08
     пÑĢиÑĩ
    0.07
    åĪ«æľī
    0.07
    çIJĨ解为
    0.07
    ctr
    0.07
     بداÙĨ
    0.07
    æīįæĺ¯çľŁæŃ£çļĦ
    0.07
     Meadows
    0.07
    æł¹æľ¬å°±æ²¡æľī
    0.07
    Activations Density 0.050%

    No Known Activations