© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20987
    Prev
    Next
    INDEX
    Explanations

    times with am or pm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dini
    -0.07
    æĸ¹ãģĮèī¯ãģĦ
    -0.07
    ufr
    -0.06
     personel
    -0.06
     siny
    -0.06
     offending
    -0.06
    à¦ķà§įষà§ĩ
    -0.06
    ucÃŃa
    -0.06
    Äĩ
    -0.06
    ynı
    -0.06
    POSITIVE LOGITS
    yp
    0.06
    ren
    0.05
     erle
    0.05
    ock
    0.05
    å£ģ
    0.05
    6
    0.04
    éĢĢ
    0.04
     Pand
    0.04
    sw
    0.04
    æĦŁ
    0.04
    Activations Density 0.030%

    No Known Activations