© 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. 19353
    Prev
    Next
    INDEX
    Explanations

    6

    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
    ines
    -0.06
     Marino
    -0.06
    agon
    -0.06
    ÙĪارÙĩ
    -0.06
    len
    -0.06
    inish
    -0.05
    uncul
    -0.05
    Referensi
    -0.05
    lenme
    -0.05
    wykle
    -0.05
    POSITIVE LOGITS
     slight
    0.05
    ä»ĭ
    0.05
    è¡Ĩ
    0.05
    檢
    0.05
    ovar
    0.05
    onde
    0.05
    çļİ
    0.05
    æĤ£
    0.05
    åĩłçĤ¹
    0.05
    æĦ¿
    0.05
    Activations Density 0.004%

    No Known Activations