© 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. 22271
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    Not in Any Lists

    No Comments

    Negative Logits
    alik
    -0.06
     Neu
    -0.05
     голово
    -0.05
    uden
    -0.05
    çĺį
    -0.05
    æľīä»Ģä¹Ī好å¤Ħ
    -0.05
     heureux
    -0.05
    æĸ°åĬłåĿ¡
    -0.05
    ุà¸ĩ
    -0.05
    顺ä¹ī
    -0.05
    POSITIVE LOGITS
    صب
    0.06
    mien
    0.05
    asin
    0.05
    à¸ŀ
    0.05
    ng
    0.05
    ardi
    0.05
     minorities
    0.05
    apa
    0.05
    ÑĥÑĤ
    0.05
    é¢ĦåŁĭ
    0.05
    Activations Density 0.003%

    No Known Activations