© 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. 19817
    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
    ittal
    -0.05
    äºĪ
    -0.05
    ئة
    -0.05
    åĭĭ
    -0.04
    è¿ĺæĺ¯ä¼ļ
    -0.04
    éĩij马
    -0.04
     ausgew
    -0.04
    ALTH
    -0.04
    Sync
    -0.04
    ivy
    -0.04
    POSITIVE LOGITS
    istro
    0.06
    ÑĩаÑĤ
    0.06
     **âĢ¢
    0.06
    ugu
    0.06
    blick
    0.06
    amen
    0.06
    rud
    0.06
    iders
    0.06
    æķ°ä½į
    0.06
    =current
    0.05
    Activations Density 0.000%

    No Known Activations