© 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. 16803
    Prev
    Next
    INDEX
    Explanations

    He was born

    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
    pc
    -0.06
     earliest
    -0.05
     mam
    -0.05
    big
    -0.05
    ay
    -0.05
    åĪĿæŃ¥
    -0.05
    fog
    -0.05
    bec
    -0.05
    dad
    -0.05
    pre
    -0.05
    POSITIVE LOGITS
    åĪ°èĢģ
    0.06
    ãģķãĤĮãģ¦ãģĦãģ¦
    0.06
    对åIJĦç§į
    0.06
     détru
    0.06
    tings
    0.06
    ç¼
    0.06
    opin
    0.06
     getro
    0.06
    对ä¸įåIJĮ
    0.06
    ontro
    0.06
    Activations Density 0.069%

    No Known Activations