© 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. 3128
    Prev
    Next
    INDEX
    Explanations

    proposal or propose

    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
     sometimes
    -0.10
     often
    -0.10
    æľīæŶ
    -0.09
    æľīæŶåĢĻ
    -0.09
     Sometimes
    -0.08
    å¾Ģå¾Ģ
    -0.08
    often
    -0.08
    Sometimes
    -0.08
    常常
    -0.08
     Often
    -0.08
    POSITIVE LOGITS
     envisioned
    0.13
     envis
    0.12
     proposal
    0.12
    å®ŀæĸ½æĸ¹æ¡Ī
    0.11
    çļĦæĸ¹æ¡Ī
    0.11
    åı¯è¡ĮçļĦ
    0.11
    设计æĸ¹æ¡Ī
    0.11
    æĸ¹æ¡Ī
    0.11
    æĸ¹æ¡ĪçļĦ
    0.11
     propose
    0.11
    Activations Density 0.192%

    No Known Activations