© 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. 21450
    Prev
    Next
    INDEX
    Explanations

    is regulated by

    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
    éĵ¶å±±
    -0.08
    åħ¶ä¸º
    -0.08
    orest
    -0.08
     menyar
    -0.07
    imonial
    -0.07
    ovable
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    ÙĤاعد
    -0.07
    ä¹ĭåĪĥ
    -0.07
    å°ıåĪ°
    -0.07
    POSITIVE LOGITS
     by
    0.09
    å°±çĶ±
    0.09
    ä½ĵçİ°åľ¨
    0.08
    à¹Ħà¸Ķà¹īà¸Īาà¸ģ
    0.08
     تÙĪسط
    0.08
    å½ĴåĬŁäºİ
    0.08
    建ç«ĭåľ¨
    0.08
    çĶ±é«ĺ
    0.08
    çĶ±åIJĦ
    0.08
    åıijçĶŁäºİ
    0.08
    Activations Density 0.503%

    No Known Activations