© 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. 16977
    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
    intern
    -0.06
    çĻ
    -0.06
    èݽ
    -0.05
    强çļĦ
    -0.05
    Ñıн
    -0.05
    tiers
    -0.05
    عاÙĨ
    -0.05
    اÙĨ
    -0.05
    halter
    -0.05
    COPE
    -0.05
    POSITIVE LOGITS
     chứng
    0.06
    æĦıèŃĺ
    0.06
    ÙĪÙħÙĬ
    0.05
    .fixed
    0.05
     staw
    0.05
    rim
    0.05
     prio
    0.05
    飻
    0.05
    íģIJ
    0.05
    vano
    0.05
    Activations Density 0.000%

    No Known Activations