© 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. 17284
    Prev
    Next
    INDEX
    Explanations

    asking why

    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
     fate
    -0.05
    int
    -0.05
    à¹Ĥà¸łà¸Ħ
    -0.05
    çŁ¥å·±
    -0.05
    nacz
    -0.05
    ne
    -0.05
    ess
    -0.05
    Äĥt
    -0.05
     int
    -0.05
    ma
    -0.05
    POSITIVE LOGITS
    agr
    0.06
    imed
    0.06
    µ
    0.06
    turut
    0.06
    kira
    0.06
     tát
    0.06
    estad
    0.06
    äºĨæĮĩ
    0.06
    awah
    0.06
    ä¸įäºĨçļĦ
    0.06
    Activations Density 0.283%

    No Known Activations