© 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. 21984
    Prev
    Next
    INDEX
    Explanations

    tenth album

    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
    asted
    -0.06
    ateg
    -0.06
    éĺ³
    -0.06
    ä¼Ł
    -0.06
    Æ°Æ¡ng
    -0.06
    æĭĶ
    -0.06
    spring
    -0.05
    å±ŀåľ°
    -0.05
    èĢĮåİ»
    -0.05
    imar
    -0.05
    POSITIVE LOGITS
    ä¸ĸçļĦ
    0.06
    ä½łçļĦæľĭåıĭ
    0.06
     unp
    0.05
    arg
    0.05
    ÙĦسة
    0.05
    ä¸įä»ħ
    0.05
    åģļåĩº
    0.05
    izr
    0.05
    kampf
    0.05
    èĪŀåĬ¨
    0.05
    Activations Density 0.001%

    No Known Activations