© 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. 16830
    Prev
    Next
    INDEX
    Explanations

    laws and ethics, systems, cookies, colors, phase

    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
    Not in Any Lists

    No Comments

    Negative Logits
     overall
    -0.06
    æĶ¯ä»ĺæĸ¹å¼ı
    -0.06
     maupun
    -0.05
    vs
    -0.05
    /
    -0.05
    سات
    -0.05
    DNA
    -0.05
     lẫn
    -0.05
    ãĢģ
    -0.05
    iede
    -0.05
    POSITIVE LOGITS
    avier
    0.06
    èĮ¸
    0.06
    ormais
    0.06
    adÄĽ
    0.06
    ackle
    0.06
    elig
    0.06
     seiz
    0.06
    以åħ¶
    0.06
    Enumerable
    0.06
    feit
    0.06
    Activations Density 0.057%

    No Known Activations