© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18559
    Prev
    Next
    INDEX
    Explanations

    homemaker, wife, women, his

    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
     corrup
    -0.06
     libertin
    -0.06
     Lama
    -0.05
    æĪª
    -0.05
     downstream
    -0.05
    Tem
    -0.05
    ä¸įå®ļæľŁ
    -0.05
     biro
    -0.05
    åIJĥä¸ľè¥¿
    -0.05
     tem
    -0.05
    POSITIVE LOGITS
    بات
    0.06
    åĩĿèģļ
    0.06
    ä¼łç»Ł
    0.06
    Ø·
    0.06
    ört
    0.05
    åİŁåľ°
    0.05
    traditional
    0.05
     traditional
    0.05
    oret
    0.05
    oor
    0.05
    Activations Density 0.013%

    No Known Activations