© 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. 22457
    Prev
    Next
    INDEX
    Explanations

    leadership roles

    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
    iae
    -0.06
    epass
    -0.06
     Thao
    -0.06
     despacho
    -0.06
    idis
    -0.06
    à¸Ĭà¸Ļ
    -0.06
    aea
    -0.06
    δα
    -0.06
    ikas
    -0.06
    -webpack
    -0.06
    POSITIVE LOGITS
    verture
    0.06
     leader
    0.06
     leaders
    0.06
    leaders
    0.05
    leader
    0.05
     beyond
    0.05
    Leaders
    0.05
    头æĪ´
    0.05
    é¢Ĩè¢ĸ
    0.05
     Leader
    0.05
    Activations Density 0.026%

    No Known Activations