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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19523
    Prev
    Next
    INDEX
    Explanations

    anti-Semitic variety or homophobia

    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
    对åĩĨ
    -0.06
    uid
    -0.06
    ansk
    -0.05
    ì¡°
    -0.05
    eras
    -0.05
     samb
    -0.05
    sta
    -0.05
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.05
    åľ¨åĵªåĦ¿
    -0.05
    vid
    -0.05
    POSITIVE LOGITS
    ffield
    0.06
    åºĶè¯ī
    0.06
    affen
    0.06
     consul
    0.05
    æĭľ
    0.05
    æķ´
    0.05
    à¹Ģà¸īลีà¹Īย
    0.05
     halves
    0.05
    æķ´é«Ķ
    0.05
     تعداد
    0.05
    Activations Density 0.004%

    No Known Activations