© 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. 38177
    Prev
    Next
    INDEX
    Explanations

    Purana texts

    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
    Mui
    -0.07
    æ¦
    -0.06
    æł¹æ·±
    -0.06
    èĽ
    -0.06
     tweeting
    -0.06
    GraphNode
    -0.06
    Statistic
    -0.06
     malt
    -0.06
     resta
    -0.06
    -Za
    -0.06
    POSITIVE LOGITS
    æĭĸæĭī
    0.08
    纲è¦ģ
    0.08
     excerpts
    0.08
    ataka
    0.08
     volumes
    0.08
     tract
    0.07
    éĿŀ常丰å¯Į
    0.07
    æĺ¯ä¸Ģéĥ¨
    0.07
    endra
    0.07
     rich
    0.07
    Activations Density 0.018%

    No Known Activations