© 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. 22486
    Prev
    Next
    INDEX
    Explanations

    election, layoffs, age, bombers, championship

    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
    à¸ķà¹Īà¸Ńà¹Ħà¸Ľ
    -0.06
     ses
    -0.05
    åĨ²åĬ¨
    -0.05
    åħ¼ãģŃ
    -0.05
    大è¿IJ
    -0.05
    asel
    -0.05
    æŁĦ
    -0.05
    å®ŀéĻħçļĦ
    -0.05
     خر
    -0.05
    proof
    -0.05
    POSITIVE LOGITS
    é¢Ħè§ģ
    0.07
    æĺĵ
    0.06
     ли
    0.06
    odyn
    0.05
    é¢ĦåĪ¤
    0.05
     preliminar
    0.05
    é¢ĦåħĪ
    0.05
     relay
    0.05
    é¢Ħ
    0.05
    relay
    0.05
    Activations Density 0.102%

    No Known Activations