© 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. 18584
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ais
    -0.06
    ÙĨاÙħÙĩ
    -0.06
    /email
    -0.05
    ARIABLE
    -0.05
     ,[
    -0.05
    Sor
    -0.05
    esch
    -0.05
    çĥ¤é±¼
    -0.05
    asanya
    -0.05
    que
    -0.05
    POSITIVE LOGITS
    аб
    0.06
    е
    0.06
    Ø´Ùħ
    0.06
    enzhen
    0.06
    parsed
    0.06
     substant
    0.06
     nạn
    0.05
    ullet
    0.05
    ↵                        ↵
    0.05
    ↵                ↵
    0.05
    Activations Density 0.000%

    No Known Activations