© 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. 22569
    Prev
    Next
    INDEX
    Explanations

    leading letters

    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
    uled
    -0.06
     repmat
    -0.05
     Maurit
    -0.05
    ilig
    -0.05
    å¹³æķ´
    -0.05
    Similar
    -0.05
     évolu
    -0.05
    éļıçĿĢå¹´é¾ĦçļĦå¢ŀéķ¿
    -0.05
    èĦļä¸ĭ
    -0.05
    èĦļä¸ĭçļĦ
    -0.05
    POSITIVE LOGITS
    atus
    0.06
    estik
    0.06
    åĦ¿
    0.05
    å¤ĸéľ²
    0.05
     resumed
    0.05
    çĭĻ
    0.05
     <->
    0.05
    zé
    0.05
    iÄĻ
    0.05
    åħĴ
    0.05
    Activations Density 0.006%

    No Known Activations