© 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. 20564
    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
     disipl
    -0.08
    åį¡è·¯
    -0.07
    kasse
    -0.06
    ıra
    -0.06
    ืà¸Ńà¸ĩ
    -0.06
    æĺ¯åIJĹ
    -0.06
    å©´
    -0.06
     unut
    -0.06
    ulai
    -0.06
    ventajas
    -0.06
    POSITIVE LOGITS
    pe
    0.07
    代表
    0.06
    age
    0.05
    end
    0.05
    ain
    0.05
    ÙĨدÙĩ
    0.05
     representative
    0.05
    ign
    0.05
    erg
    0.05
    irm
    0.05
    Activations Density 0.000%

    No Known Activations