© 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. 18631
    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
    "...
    -0.06
    à¹ģมà¹Īà¸Ļ
    -0.05
    ycle
    -0.05
    å½ĵå½ĵ
    -0.05
    ift
    -0.05
    inance
    -0.05
    çļĦ第
    -0.05
    ourd
    -0.05
    enstein
    -0.05
    :...
    -0.05
    POSITIVE LOGITS
    +xml
    0.05
    hs
    0.05
     dĩ
    0.05
    aturing
    0.05
    anja
    0.05
    rent
    0.05
    ingat
    0.05
    aga
    0.05
     Hal
    0.05
    ষà§įà¦Ł
    0.05
    Activations Density 0.000%

    No Known Activations