© 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. 22316
    Prev
    Next
    INDEX
    Explanations

    date, or time

    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
    th
    -0.06
    lot
    -0.06
    æĿ¥è¶Ĭ
    -0.06
    æĪijè¿ĺ
    -0.06
    椿
    -0.06
    enes
    -0.06
    bing
    -0.06
    ssen
    -0.06
    å°¹
    -0.05
    avat
    -0.05
    POSITIVE LOGITS
     honey
    0.05
    æĥķ
    0.05
    大米
    0.05
    çļĦæĿ¡ä»¶ä¸ĭ
    0.05
    mere
    0.05
    éĤ£ä¸ĢåĪ»
    0.05
    -dist
    0.05
    ente
    0.05
     hon
    0.05
    avage
    0.05
    Activations Density 0.001%

    No Known Activations