© 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. 19596
    Prev
    Next
    INDEX
    Explanations

    contrast and related concepts

    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
    åįķæĸ¹éĿ¢
    -0.06
    æĺ¯ä¸Ģ个éĿŀ常
    -0.05
    иÑĤелÑĮÑģÑĤва
    -0.05
    è¿ij
    -0.05
    stream
    -0.05
    ergi
    -0.05
    ä¸Ģåıij
    -0.05
     jsonify
    -0.05
    åıĺæĪIJäºĨä¸Ģ个
    -0.05
    è¿ŀ
    -0.05
    POSITIVE LOGITS
    ed
    0.08
    edan
    0.07
    Ùĩ
    0.07
    å£ĵ
    0.06
    ï¸İ
    0.06
     sharply
    0.06
    лÑĮÑĤ
    0.06
    éĹ®é¢ĺæĿ¥äºĨ
    0.06
    ìį¨
    0.06
    edas
    0.05
    Activations Density 0.008%

    No Known Activations