© 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. 21428
    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
    engers
    -0.07
    çıŃåĪĹ
    -0.07
    agar
    -0.06
    akse
    -0.06
    IDER
    -0.06
    elay
    -0.06
    ardin
    -0.06
    agara
    -0.06
    idders
    -0.06
    agi
    -0.06
    POSITIVE LOGITS
    orz
    0.06
     National
    0.05
     massively
    0.05
    National
    0.05
    æĻ®æŀĹ
    0.05
    åIJİæİĴ
    0.05
    å¨ģ
    0.05
     неплоÑħо
    0.05
     vastly
    0.05
     оÑĤÑĤ
    0.05
    Activations Density 0.001%

    No Known Activations