© 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. 18903
    Prev
    Next
    INDEX
    Explanations

    quotation marks or names

    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
    ÙĪÙī
    -0.07
    rawn
    -0.07
    çĤ¹æѤ
    -0.07
     disi
    -0.07
    à¸Ħรัà¹īà¸ĩสุà¸Ķà¸Ĺà¹īาย
    -0.06
    ÑĤаÑĤа
    -0.06
    isas
    -0.06
    ssue
    -0.06
    åı«äºº
    -0.06
    ritten
    -0.06
    POSITIVE LOGITS
    åĨį
    0.05
    .Byte
    0.05
    (s
    0.05
    ä¹Łèĥ½
    0.05
    -
    0.05
     ex
    0.05
    éĤ£äºĽ
    0.05
    å¼¹
    0.04
    "
    0.04
    æĿĢ
    0.04
    Activations Density 0.002%

    No Known Activations