© 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. 19179
    Prev
    Next
    INDEX
    Explanations

    blurb or hook

    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
    LOGY
    -0.06
    é¦ĸ次
    -0.06
    ä¸ĢåŃĹ
    -0.06
    gelt
    -0.06
     primi
    -0.05
     ÙĦÙĦÙħرة
    -0.05
    é¢Ħä»ĺ
    -0.05
    åŃĹçľ¼
    -0.05
     VEND
    -0.05
    ahu
    -0.05
    POSITIVE LOGITS
    ablo
    0.06
    åįł
    0.05
    olia
    0.05
    gia
    0.05
     opn
    0.05
    _clause
    0.05
    esti
    0.05
    ilia
    0.05
     pm
    0.05
    untime
    0.05
    Activations Density 0.002%

    No Known Activations