© 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. 22592
    Prev
    Next
    INDEX
    Explanations

    financial difficulty, affordability, poverty

    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
    人çĶŁ
    -0.06
    лÑij
    -0.06
    eck
    -0.06
    à¹Ģลส
    -0.06
    ifer
    -0.05
    èģ
    -0.05
    _claim
    -0.05
    obot
    -0.05
    æIJľçĭĹ
    -0.05
     conv
    -0.05
    POSITIVE LOGITS
    alc
    0.06
    ims
    0.06
    uff
    0.06
    çªĺ
    0.06
    uffs
    0.05
     poverty
    0.05
    ntl
    0.05
    çļĦæīĭ段
    0.05
    ä¸įæĢķ
    0.05
    fälle
    0.05
    Activations Density 0.024%

    No Known Activations