© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29700
    Prev
    Next
    INDEX
    Explanations

    chemical names and structures

    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
    vlak
    -0.08
     usk
    -0.08
     histogram
    -0.08
    Launcher
    -0.08
    oghi
    -0.08
     histograms
    -0.07
    launcher
    -0.07
    çĶ¨èĩªå·±
    -0.07
    ibra
    -0.07
    è¿Ļç§įçݰ象
    -0.07
    POSITIVE LOGITS
    æĺ¯æĮĩåľ¨
    0.07
    æĮĩçļĦæĺ¯
    0.07
    æĺ¯æĮĩ
    0.06
    å¾Ģåīį
    0.06
     defined
    0.06
    neb
    0.06
    éĤ£ä¸ªæŶåĢĻ
    0.06
    æĭĶ
    0.06
     wise
    0.06
    æĮĩå®ļ
    0.06
    Activations Density 0.001%

    No Known Activations