© 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. 16641
    Prev
    Next
    INDEX
    Explanations

    rocket propulsion and engines

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    éĺ²èĮĥ
    -0.05
    oire
    -0.05
     tri
    -0.05
     inv
    -0.04
     alle
    -0.04
    mit
    -0.04
     pattern
    -0.04
     polygon
    -0.04
     اÙĨع
    -0.04
     ins
    -0.04
    POSITIVE LOGITS
     Rocket
    0.07
     Fountain
    0.07
    argo
    0.06
    лÑıÑĢ
    0.06
     rocket
    0.06
    eros
    0.06
     Rockets
    0.06
    uruh
    0.06
     rockets
    0.06
    çĦ°
    0.06
    Activations Density 0.019%

    No Known Activations