© 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. 33407
    Prev
    Next
    INDEX
    Explanations

    assume, lets, say, referred

    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
     dér
    -0.09
    å¾Ģå¾Ģä¼ļ
    -0.08
    è¿ľæ¯Ķ
    -0.08
    hão
    -0.08
    æīįæĺ¯çľŁæŃ£çļĦ
    -0.08
    æł¹æľ¬ä¸įæĺ¯
    -0.08
    åį´ä¾ĿçĦ¶
    -0.07
    ç»ıæµİå¸Ī
    -0.07
    alet
    -0.07
    rier
    -0.07
    POSITIVE LOGITS
    认为æĺ¯
    0.12
    认为
    0.11
     assume
    0.10
    åģĩ设
    0.09
    assume
    0.09
     assumed
    0.09
     assumes
    0.09
    è¿ijä¼¼
    0.09
     assuming
    0.09
     Assume
    0.09
    Activations Density 0.029%

    No Known Activations