© 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. 17169
    Prev
    Next
    INDEX
    Explanations

    job loss and layoffs

    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
    wegen
    -0.07
    äºijé¾Ļ
    -0.07
    ograd
    -0.07
    管æĬ¤
    -0.06
    empre
    -0.06
    空èĻļ
    -0.06
     Kolej
    -0.06
    æµĴ
    -0.06
    paring
    -0.06
    gé
    -0.06
    POSITIVE LOGITS
    ieve
    0.06
     Ok
    0.05
    Ok
    0.05
    çĨĻ
    0.05
    éĢĢ
    0.05
     ok
    0.05
     Con
    0.05
    çŀ
    0.05
     F
    0.05
    æŁIJ
    0.05
    Activations Density 0.001%

    No Known Activations