© 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. 18951
    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
     yourselves
    -0.06
    ering
    -0.06
    æĦģ
    -0.05
    æĹłè¾ľ
    -0.05
    ahlen
    -0.05
     spia
    -0.05
    身ä¸ĬçļĦ
    -0.05
    amus
    -0.05
    èĩ³äºİ
    -0.05
    amiÄĻ
    -0.05
    POSITIVE LOGITS
    imp
    0.06
    aland
    0.05
    رد
    0.05
    nee
    0.05
    icha
    0.05
    ãģŁãĤī
    0.05
    被åĬ¨
    0.05
    æ¶Ł
    0.05
    åĽłçĹħ
    0.05
    пÑĢов
    0.05
    Activations Density 0.000%

    No Known Activations