© 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. 58517
    Prev
    Next
    INDEX
    Explanations

    connecting words

    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
    ç«Ł
    -0.06
    æľĿ
    -0.06
    çIJĨ论ä¸İ
    -0.06
    жив
    -0.06
    pet
    -0.06
    该åĨħ容
    -0.06
    ç«ŁçĦ¶
    -0.06
    xxxxxxxx
    -0.06
     [
    -0.05
     ger
    -0.05
    POSITIVE LOGITS
     demás
    0.09
     غÙĬرÙĩ
    0.09
     ë§Īì°¬ê°Ģì§Ģë¡ľ
    0.09
    åĨĻå¾Ĺ
    0.08
    ocken
    0.08
    ½Ķ
    0.08
    èĩªè¾¾
    0.08
    ç©Į
    0.08
    æĹ¥ä»İ
    0.08
     especialmente
    0.08
    Activations Density 0.035%

    No Known Activations