© 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. 16582
    Prev
    Next
    INDEX
    Explanations

    deep/strong/pure feelings and qualities

    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
     classification
    -0.06
     Personally
    -0.05
    PROFILE
    -0.05
    åı¯æĥľ
    -0.05
    ermal
    -0.05
    ames
    -0.05
    æıIJä¾ĽæĶ¯æĮģ
    -0.05
     pesso
    -0.05
    athy
    -0.05
     Classification
    -0.05
    POSITIVE LOGITS
    æĹłå¸¸
    0.06
    ering
    0.06
    icking
    0.06
    à¸ķร
    0.05
    å¾ĹéĿŀ常
    0.05
    ä¸įå½ĵ
    0.05
    å¾ĹæĽ´åĬł
    0.05
    venu
    0.05
    管æīĢ
    0.05
    å¾Ĺå½ĵ
    0.05
    Activations Density 0.007%

    No Known Activations