© 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. 22160
    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
     van
    -0.05
     ort
    -0.05
    u
    -0.05
    ëĭ¤ëĭĪ
    -0.04
    ÑĢоб
    -0.04
    Ń
    -0.04
     des
    -0.04
     Orth
    -0.04
     H
    -0.04
     dol
    -0.04
    POSITIVE LOGITS
    使ä¹ĭ
    0.07
    кÑĬ
    0.07
    è¨Ģ
    0.06
    ayakan
    0.06
    ivot
    0.06
    é¡ĺ
    0.06
    putusan
    0.06
    üllen
    0.06
    ornado
    0.06
    ield
    0.06
    Activations Density 0.000%

    No Known Activations