© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22292
    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
    å¿Ĺ
    -0.07
    orando
    -0.06
    istros
    -0.06
    engesch
    -0.06
    udies
    -0.06
    áter
    -0.05
    runner
    -0.05
     виз
    -0.05
    ака
    -0.05
     lib
    -0.05
    POSITIVE LOGITS
     upt
    0.06
    orma
    0.05
    angelo
    0.05
    мÑı
    0.05
    inu
    0.05
    ng
    0.05
    LIN
    0.05
    çĽĺä¸Ń
    0.05
     upset
    0.05
    éĨīäºĨ
    0.05
    Activations Density 0.013%

    No Known Activations