© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20650
    Prev
    Next
    INDEX
    Explanations

    in + noun/phrase

    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
    /current
    -0.06
     пови
    -0.05
    weiÃŁ
    -0.05
    è·ĭ
    -0.05
    cassert
    -0.05
     gê
    -0.05
    anak
    -0.05
     ÑĨив
    -0.05
    ater
    -0.05
    çİ°åľ¨çļĦ
    -0.05
    POSITIVE LOGITS
    isser
    0.06
    ptest
    0.06
    ispens
    0.06
    sey
    0.05
     tim
    0.05
     plays
    0.05
    ibold
    0.05
    angsa
    0.05
    isque
    0.05
    plays
    0.05
    Activations Density 0.021%

    No Known Activations