© 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. 22541
    Prev
    Next
    INDEX
    Explanations

    ideas and projects

    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
    horn
    -0.06
    วà¸Ķ
    -0.06
     personn
    -0.06
    jak
    -0.06
    ounc
    -0.06
    çIJĨ念
    -0.06
    ä¼
    -0.06
    atical
    -0.06
    æĸ¹æĸ¹éĿ¢
    -0.06
    åħŃ大
    -0.06
    POSITIVE LOGITS
     between
    0.05
     implication
    0.05
     implications
    0.05
    积
    0.05
    0.05
    缮
    0.05
    cope
    0.04
    Me
    0.04
     unm
    0.04
     performed
    0.04
    Activations Density 0.006%

    No Known Activations