© 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. 44518
    Prev
    Next
    INDEX
    Explanations

    setup with, narcotic otic, aggressive behaviour, main wings, magnetic tape, reference elution, material owing, Codewars, Power Supply

    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
    jør
    -0.07
     âĤ©
    -0.07
    lijf
    -0.07
    æºIJåľ°
    -0.07
    æŁ¥æĶ¶
    -0.07
    üsü
    -0.07
    eggio
    -0.07
    oris
    -0.07
    abet
    -0.06
    estar
    -0.06
    POSITIVE LOGITS
    åѦ
    0.07
    ä¹Łå°±æĺ¯
    0.07
    è±
    0.06
    cliffe
    0.06
     pez
    0.06
     Dich
    0.06
    è¿ĩç¥ŀ
    0.06
    伤
    0.06
    æı
    0.06
    èŁ
    0.06
    Activations Density 0.271%

    No Known Activations