© 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. 16644
    Prev
    Next
    INDEX
    Explanations

    song titles and lyrics

    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
    éļ¾
    -0.05
     st
    -0.05
    解
    -0.05
    å¯Ĵ
    -0.05
    åıijæĮ¥
    -0.05
     guts
    -0.05
    åĽ¢
    -0.05
    大
    -0.05
    ç³Ĭæ¶Ĥ
    -0.05
    èİ«
    -0.05
    POSITIVE LOGITS
    å¿Ĺæĺİ
    0.07
    ihat
    0.07
    OMATIC
    0.07
    omatik
    0.07
    óp
    0.06
    éĻĮ
    0.06
     popr
    0.06
    LBL
    0.06
    atico
    0.06
    cientes
    0.06
    Activations Density 0.047%

    No Known Activations