© 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. 3741
    Prev
    Next
    INDEX
    Explanations

    and, also

    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
     bowiem
    -0.11
     ugyanis
    -0.11
     infatti
    -0.11
     nämlich
    -0.10
    讲çļĦæĺ¯
    -0.10
     totiž
    -0.09
    并讲è¯Ŀ
    -0.08
     aga
    -0.08
    åħ³éĹŃçªĹåı£
    -0.08
    usband
    -0.08
    POSITIVE LOGITS
    缸åºĶ
    0.12
    缸åºĶçļĦ
    0.11
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    0.09
    çĶ±æѤ
    0.09
    以æŃ¤ä¸º
    0.09
     thereafter
    0.09
    以æѤ
    0.08
     afterward
    0.08
    缸æĩī
    0.08
    åł´åIJĪ
    0.08
    Activations Density 0.010%

    No Known Activations