© 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. 20415
    Prev
    Next
    INDEX
    Explanations

    Russian words ending in -ая or -ие

    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
    enton
    -0.06
    åĴĮæĶ¿çŃĸ
    -0.05
     bách
    -0.05
    åı¸æ³ķè¡ĮæĶ¿
    -0.05
    å¸ĮæľĽä½łä»¬
    -0.05
     Yesterday
    -0.05
    设计åħ¬åı¸
    -0.05
    å¾Īå¤ļéĹ®é¢ĺ
    -0.05
     Ñģка
    -0.05
    pies
    -0.05
    POSITIVE LOGITS
    onian
    0.06
    ukk
    0.06
    çī¹
    0.05
    å¹²
    0.05
    ije
    0.05
    ç´ĭ
    0.05
    åĩĨ
    0.05
    å®ı
    0.05
    èģĮ
    0.05
    éļ¾
    0.05
    Activations Density 0.029%

    No Known Activations