© 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. 20335
    Prev
    Next
    INDEX
    Explanations

    devoted, sacrificed, worked

    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
    igo
    -0.06
    ÎŃλ
    -0.06
    뢰
    -0.06
    ä»İçİ°åľ¨å¼Ģå§ĭ
    -0.06
     Sebast
    -0.06
    ابس
    -0.05
     selle
    -0.05
    åĨ·æ°´
    -0.05
    代çIJĨæľįåĬ¡
    -0.05
    ÑĩиÑģли
    -0.05
    POSITIVE LOGITS
    .windows
    0.05
    opp
    0.05
    æĺłçħ§
    0.05
    å¿į
    0.05
    åĮħ容
    0.05
    ä»ĺåĩºçļĦ
    0.05
    æݢ索
    0.05
    妥
    0.05
     пÑĭ
    0.05
     giveaways
    0.05
    Activations Density 0.044%

    No Known Activations