© 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. 21050
    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
    æĮļ
    -0.06
    żd
    -0.06
    eho
    -0.06
    adelphia
    -0.06
    æľŁåĨħ
    -0.06
     bấy
    -0.06
    gues
    -0.06
    edin
    -0.06
    hone
    -0.06
    dig
    -0.06
    POSITIVE LOGITS
    Âł
    0.05
     (
    0.05
    i
    0.05
    मà¥į
    0.05
    ò
    0.05
     relevant
    0.05
     primitive
    0.05
    侧éĩį
    0.05
    ,
    0.05
    Ľ
    0.05
    Activations Density 0.000%

    No Known Activations