© 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. 16599
    Prev
    Next
    INDEX
    Explanations

    delegating or outsourcing tasks

    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
    claimer
    -0.07
    elus
    -0.07
    irts
    -0.07
     affian
    -0.07
    rection
    -0.07
    elts
    -0.07
    ruc
    -0.07
    æĭĸç´¯
    -0.07
    ldb
    -0.07
    mdl
    -0.07
    POSITIVE LOGITS
    æĶ¾è¿ĩ
    0.06
    0.06
     concern
    0.05
    zie
    0.05
     chance
    0.05
    ä¸Ģæĭį
    0.05
     (
    0.05
     const
    0.05
     far
    0.05
     concerns
    0.05
    Activations Density 0.004%

    No Known Activations