© 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. 21982
    Prev
    Next
    INDEX
    Explanations

    spark, pyspark, spark.sql, spark.read

    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
    çİĽ
    -0.06
    èµĸ
    -0.05
    ix
    -0.05
    IMA
    -0.05
    座ä¸Ĭ
    -0.05
     má
    -0.05
    æ¯ķ
    -0.05
     Arr
    -0.05
     v
    -0.05
     arrangements
    -0.05
    POSITIVE LOGITS
    agnes
    0.07
    ÙĦاء
    0.06
    ysl
    0.06
    entang
    0.06
    sheets
    0.06
    engel
    0.06
    ucz
    0.06
    æĭĸ
    0.06
    ÙĦÙĬÙħ
    0.06
    otten
    0.06
    Activations Density 0.003%

    No Known Activations