© 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. 48830
    Prev
    Next
    INDEX
    Explanations

    triple quoted strings or comments

    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
    urier
    -0.08
    aurus
    -0.08
     mier
    -0.08
    çĪ±å²Ĺ
    -0.08
    大éĥ¨ä»½
    -0.07
    çª
    -0.07
    èĪ
    -0.07
    æµĭéĩı
    -0.07
    aisin
    -0.07
    asco
    -0.07
    POSITIVE LOGITS
    ä¸İçİ°å®ŀ
    0.07
    åıī
    0.07
    代ä¹ĭ
    0.07
    aked
    0.07
    æĭ·
    0.07
     Pov
    0.06
    el
    0.06
    çĭIJ
    0.06
    è¿Ļéģĵ
    0.06
    ä¸İæĸ¹æ³ķ
    0.06
    Activations Density 0.001%

    No Known Activations