© 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. 16799
    Prev
    Next
    INDEX
    Explanations

    particular conditions, child, panel

    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
    inting
    -0.06
    ukup
    -0.06
    кÑĸн
    -0.06
    welt
    -0.05
    plier
    -0.05
    azing
    -0.05
    Ú¯ÛĮر
    -0.05
    kup
    -0.05
    ÑĢед
    -0.05
    ezz
    -0.05
    POSITIVE LOGITS
     cap
    0.05
    å´ĩ
    0.05
    é¦
    0.05
    ç§ģæĪ¿
    0.05
     angular
    0.05
    æĸ¹
    0.05
    shares
    0.05
    trad
    0.05
    çļĦæľ¬
    0.05
    ipa
    0.05
    Activations Density 0.011%

    No Known Activations