© 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. 17073
    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
    ей
    -0.05
    ç§ijåѦåıijå±ķ
    -0.05
    arren
    -0.05
     maintained
    -0.05
    åĽºä»¶
    -0.05
    ä½ĨéļıçĿĢ
    -0.05
    第ä¸Ģ项
    -0.05
    enas
    -0.05
    avid
    -0.05
    7
    -0.04
    POSITIVE LOGITS
     riv
    0.06
    erder
    0.06
    ä¸Ģè¶Ł
    0.06
    æ¡¥
    0.06
    çĵľ
    0.06
    åIJĮæľŁ
    0.06
     Wolfsburg
    0.06
    tte
    0.06
     Gegenwart
    0.06
    uha
    0.05
    Activations Density 0.000%

    No Known Activations