© 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. 28613
    Prev
    Next
    INDEX
    Explanations

    combustion gases, vendor credit, recycled paper

    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
    ady
    -0.07
    ä¹Łå¥½
    -0.07
    ösen
    -0.06
    缮ä¸Ń
    -0.06
    æĺ¯åĽłä¸º
    -0.06
    waard
    -0.06
    bay
    -0.06
    ç½ijé¦ĸ页
    -0.06
    ä½ĵåĮĸ
    -0.06
     retirada
    -0.06
    POSITIVE LOGITS
     appunto
    0.09
     cosidd
    0.07
    éĹ»
    0.07
    uelas
    0.07
    unto
    0.07
     Corso
    0.07
    èģŀ
    0.07
     sogenannte
    0.06
     sogen
    0.06
    è¦ģä¹Ī
    0.06
    Activations Density 0.243%

    No Known Activations