© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19632
    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
     unle
    -0.06
     Ung
    -0.06
    ewise
    -0.05
    æĢ»åĮ»éĻ¢
    -0.05
    доÑħ
    -0.05
    ä¹ĺé£İ
    -0.05
    éĤ£ä¹Ī好
    -0.05
    åIJIJè¡Ģ
    -0.05
    çĥŃçĪ±ç¥ĸåĽ½
    -0.05
     Khang
    -0.05
    POSITIVE LOGITS
    ç±³åħ¶æŀĹ
    0.06
    éĩįä¸Ńä¹ĭéĩį
    0.06
    HORT
    0.05
    enstr
    0.05
    èĬ¸
    0.05
    elman
    0.05
    órica
    0.05
    اÙħر
    0.05
    بÙĬÙĨ
    0.05
    pace
    0.05
    Activations Density 0.000%

    No Known Activations