© 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. 19294
    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
    дли
    -0.06
    sth
    -0.06
    ä¸īåįģå¹´
    -0.06
    olina
    -0.05
    estre
    -0.05
    治好
    -0.05
    essler
    -0.05
    orious
    -0.05
    pel
    -0.05
    ÏĦε
    -0.05
    POSITIVE LOGITS
    laut
    0.07
    éĹ´çļĦ
    0.06
    akangan
    0.06
    泡沫
    0.06
    éĹ´
    0.05
    æ±°
    0.05
    ëħIJ
    0.05
    à¸ŀร
    0.05
     ordin
    0.05
    å·¥ç¨ĭ大åѦ
    0.05
    Activations Density 0.000%

    No Known Activations