© 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. 20376
    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
    tora
    -0.07
    ÃįN
    -0.07
    èo
    -0.06
     Gelt
    -0.06
    неÑĨ
    -0.06
     uyg
    -0.06
    lite
    -0.06
    culares
    -0.06
    uraa
    -0.06
    ategori
    -0.06
    POSITIVE LOGITS
     Tri
    0.06
    0.06
    tri
    0.06
    Tri
    0.06
    SD
    0.05
    ’
    0.05
    on
    0.05
    S
    0.05
    åĪĨåĪ«
    0.05
    ide
    0.05
    Activations Density 0.000%

    No Known Activations