© 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. 19203
    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
     simultaneously
    -0.06
    å°Ĩæľī
    -0.05
     secondary
    -0.05
     Kern
    -0.05
     départ
    -0.05
     godere
    -0.05
    ilván
    -0.05
    åIJĮæŶå°Ĩ
    -0.05
     b
    -0.05
     néanmoins
    -0.05
    POSITIVE LOGITS
    ç·Ĵ
    0.07
    çŀ
    0.07
    alnya
    0.06
    nable
    0.06
    atalog
    0.06
    áŀŁáŁĭ
    0.06
     messed
    0.06
    éĻIJé¢Ŀ
    0.06
     лим
    0.06
    èIJ©
    0.06
    Activations Density 0.000%

    No Known Activations