© 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. 22578
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    綴
    -0.07
     amt
    -0.06
    amd
    -0.06
    å°İ
    -0.06
    etzen
    -0.06
    åħ¶ä¹IJ
    -0.06
    导
    -0.06
    illum
    -0.06
    åºĦéķĩ
    -0.06
     reap
    -0.06
    POSITIVE LOGITS
    æ¯ķ
    0.05
    çĥĤ
    0.05
    orig
    0.05
    çī©çļĦ
    0.05
    éĢĤ
    0.05
    alar
    0.05
    çī©
    0.05
    åIJĥ
    0.05
    çķ¢
    0.05
    éĹ¹
    0.05
    Activations Density 0.000%

    No Known Activations