© 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. 20457
    Prev
    Next
    INDEX
    Explanations

    č used

    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
    Ø©
    -0.09
    à¸ģารà¸ĵà¹Į
    -0.07
    lement
    -0.07
    ils
    -0.07
    lee
    -0.06
    -0.06
    à§įত
    -0.06
    ÏĤ
    -0.06
    ting
    -0.06
    errupt
    -0.06
    POSITIVE LOGITS
    ÙĬ
    0.07
    er
    0.07
    и
    0.07
    ing
    0.07
    iog
    0.07
    outh
    0.07
    ingk
    0.06
    Ù°
    0.06
    åħ¼æĢ»ç»ıçIJĨ
    0.06
    oring
    0.06
    Activations Density 0.020%

    No Known Activations