© 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. 18617
    Prev
    Next
    INDEX
    Explanations

    N-methyl or N-ethyl groups

    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
    ä¹ĺ
    -0.06
     Tribut
    -0.06
    arel
    -0.05
    brace
    -0.05
    hands
    -0.05
    à¸Ħร
    -0.05
    adena
    -0.05
    èį¡
    -0.05
    koh
    -0.05
    öl
    -0.05
    POSITIVE LOGITS
    æģķ
    0.05
    ä¸Ģå®ļéĩıçļĦ
    0.05
    å°Ķå¤ļ
    0.05
    schlä
    0.05
    moni
    0.05
    ÙĬÙĨÙĩ
    0.05
    ucket
    0.05
    avier
    0.05
    erot
    0.05
    åį¸
    0.05
    Activations Density 0.018%

    No Known Activations