© 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. 21667
    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
     technical
    -0.06
    ặt
    -0.06
     asia
    -0.06
    technical
    -0.06
     sizing
    -0.06
     Asia
    -0.05
    ädchen
    -0.05
    aista
    -0.05
    глÑıд
    -0.05
    ETA
    -0.05
    POSITIVE LOGITS
    åĩłä¹İ没æľī
    0.06
    utils
    0.06
    rasil
    0.05
     Collins
    0.05
    ä¸įåĩºåİ»
    0.05
     barely
    0.05
    afür
    0.05
    вÑĭв
    0.05
     seg
    0.05
    ÏĦÏį
    0.05
    Activations Density 0.000%

    No Known Activations