© 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. 14661
    Prev
    Next
    INDEX
    Explanations

    groups of samples or classes

    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
    _bits
    -0.07
    rides
    -0.07
    åľ¨æł¡æľŁéĹ´
    -0.07
    æķ´å¥Ĺ
    -0.07
    _binding
    -0.07
    Ñĥго
    -0.07
    åĽ½éĻħåĮĸçļĦ
    -0.07
    个人è¡Į为
    -0.07
    _content
    -0.06
    åħĨ
    -0.06
    POSITIVE LOGITS
    æł·æľ¬
    0.09
    æĬ½æł·
    0.08
     statist
    0.08
     unequal
    0.08
    sample
    0.07
    竺
    0.07
     pooled
    0.07
    æĸ¹å·®
    0.07
     samples
    0.07
    -sample
    0.07
    Activations Density 0.008%

    No Known Activations