© 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. 16568
    Prev
    Next
    INDEX
    Explanations

    garbageman

    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
    unos
    -0.07
    åĨħè¿Ľè¡Į
    -0.06
    触
    -0.05
    ĥ
    -0.05
    reja
    -0.05
    æŃ»ä¸į
    -0.05
    пÑĥ
    -0.05
    osph
    -0.05
    ç«Ļå¼ı
    -0.05
    ðŁĴ
    -0.05
    POSITIVE LOGITS
     rembourse
    0.06
    okok
    0.06
    åĴĮè§ĦèĮĥ
    0.05
    åĵįåºĶ
    0.05
    -gay
    0.05
    åĴĮä¸Ģ
    0.05
    init
    0.05
    logo
    0.05
    éĺ¿åį¡
    0.05
     Alfon
    0.05
    Activations Density 0.013%

    No Known Activations