© 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. 19675
    Prev
    Next
    INDEX
    Explanations

    few, group, percentage, handful

    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
    RI
    -0.06
    iche
    -0.06
     phases
    -0.05
    å¤ı
    -0.05
    ãģĮãģ¡
    -0.05
    ãģĭãĤı
    -0.05
    typeof
    -0.05
    beste
    -0.05
     {.
    -0.05
    amu
    -0.05
    POSITIVE LOGITS
    ç§ĺ
    0.06
    -anchor
    0.06
    à¸ĺ
    0.06
     True
    0.05
     пÑĢоÑĨенÑĤа
    0.05
     out
    0.05
    ä¸įéĢĢ
    0.05
    çµIJ
    0.05
    åIJįåĪ©
    0.05
    çļİ
    0.05
    Activations Density 0.044%

    No Known Activations