© 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. 25229
    Prev
    Next
    INDEX
    Explanations

    subtle changes or variations

    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
    деб
    -0.08
    ίδα
    -0.07
    æľĢå¿«
    -0.07
    èĥĮéĿł
    -0.06
    åĪ·æĸ°
    -0.06
     explicitly
    -0.06
    ลัà¸ļ
    -0.06
     itib
    -0.06
    æľĢæĹ©
    -0.06
    æľĢ大éĻIJ度
    -0.06
    POSITIVE LOGITS
    å¾®å°ıçļĦ
    0.11
     slightest
    0.10
    æķıæĦŁ
    0.10
    ç»Ĩå¾®
    0.10
    ensitive
    0.10
    ç¨įæľī
    0.09
     sensitive
    0.09
    ç»ĨèĬĤ
    0.09
    对å°ı
    0.09
    æķıæĦŁçļĦ
    0.09
    Activations Density 0.048%

    No Known Activations