© 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. 16679
    Prev
    Next
    INDEX
    Explanations

    desires Company reported

    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
    å°½æľī
    -0.05
     offert
    -0.05
     оплаÑĤе
    -0.05
     sejauh
    -0.05
    åħ·æľīä¸Ģå®ļçļĦ
    -0.05
     pon
    -0.05
     airing
    -0.05
     annoncer
    -0.05
    åĮħæīİ
    -0.05
    èĩªå·±å¯¹
    -0.05
    POSITIVE LOGITS
    ç¡®
    0.06
    ัà¸ģษà¹Į
    0.06
    æĢ§å¼º
    0.06
    iol
    0.06
    awah
    0.06
    è¿ħçĮĽ
    0.06
    ernaut
    0.06
    trip
    0.05
    æĪĺçķ¥è§ĦåĪĴ
    0.05
    னà¯Ī
    0.05
    Activations Density 0.001%

    No Known Activations