© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52084
    Prev
    Next
    INDEX
    Explanations

    "secret" / alpha-secretase

    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
    Negative Logits
    æĪij们就è¦ģ
    -0.08
    estre
    -0.07
    eggi
    -0.07
    åħ¸åŀĭçļĦ
    -0.07
    laves
    -0.07
    åĤħ
    -0.07
    elry
    -0.07
    unga
    -0.07
    à¹ĩ
    -0.06
    วà¸ĩ
    -0.06
    POSITIVE LOGITS
    å²ģå²ģ
    0.09
    åĪ«èĩ´
    0.07
    飦å°Ķ
    0.06
    npc
    0.06
    edException
    0.06
    æį®
    0.06
    usercontent
    0.06
    CHA
    0.06
    _dicts
    0.06
     Sungai
    0.06
    Activations Density 0.034%

    No Known Activations