© 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. 20140
    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
     care
    -0.06
     pol
    -0.05
     lan
    -0.05
     vir
    -0.05
     compar
    -0.05
     os
    -0.05
    ä¸ĭçļĦ
    -0.05
    ikt
    -0.05
     bas
    -0.05
     ê³Ħ
    -0.05
    POSITIVE LOGITS
    anam
    0.06
    anic
    0.06
     аза
    0.06
    æij©æł¹
    0.06
    çIJ¶
    0.06
     unint
    0.06
    -Col
    0.06
    teria
    0.06
    ldb
    0.06
    arate
    0.06
    Activations Density 0.000%

    No Known Activations