© 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. 11147
    Prev
    Next
    INDEX
    Explanations

    unlimited or infinite quantity

    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
    ä¸Ģæĸ°
    -0.09
    -dismiss
    -0.08
    geb
    -0.08
     niem
    -0.08
    insk
    -0.08
    ìĿ´ìĬ¤
    -0.08
    nique
    -0.08
    å®Įæķ´åľ°
    -0.07
    å®Įåħ¨ä¸įåIJĮçļĦ
    -0.07
    ä¾ĭè¡Į
    -0.07
    POSITIVE LOGITS
     تÙĤرÙĬب
    0.11
     theoretically
    0.09
     infinite
    0.09
    æĹłéĻIJçļĦ
    0.08
    çIJĨ论ä¸Ĭ
    0.08
    æĹłå°½
    0.08
     unlimited
    0.08
     infinit
    0.08
     sayıda
    0.07
     infinitely
    0.07
    Activations Density 0.040%

    No Known Activations