© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21699
    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
    è·Ŀ
    -0.06
    çĽ¸å¯¹èĢĮè¨Ģ
    -0.05
    orth
    -0.05
    æĬĺ
    -0.05
    å°ļ
    -0.05
    éviter
    -0.05
    çĨ
    -0.05
    çĽ¸å¯¹
    -0.05
     D
    -0.05
    “
    -0.05
    POSITIVE LOGITS
     Cassidy
    0.07
    BREAK
    0.07
    ordes
    0.06
     CONCE
    0.06
    IFICA
    0.06
     Presup
    0.06
    ä¹ĭå®Ŀ
    0.06
    gabe
    0.06
    اÙĤ
    0.06
    ingg
    0.06
    Activations Density 0.000%

    No Known Activations