© 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. 19370
    Prev
    Next
    INDEX
    Explanations

    javascript var usage

    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
    urch
    -0.06
    scha
    -0.06
    ance
    -0.06
    boarding
    -0.06
    ada
    -0.06
    ilib
    -0.05
    ona
    -0.05
     Demi
    -0.05
    ancel
    -0.05
    ulence
    -0.05
    POSITIVE LOGITS
    å¾Ģ
    0.06
    å«Į
    0.06
    оек
    0.06
     outlook
    0.05
    à¹īà¸ĩ
    0.05
    ujan
    0.05
    åĶ¯ä¸Ģ
    0.05
    θηÏĥη
    0.05
    äºĴ
    0.05
    ravi
    0.05
    Activations Density 0.029%

    No Known Activations