© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17700
    Prev
    Next
    INDEX
    Explanations

    javascript code snippets

    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
    ибо
    -0.06
     matter
    -0.06
     Matter
    -0.06
    -fired
    -0.06
    -cols
    -0.05
     Matters
    -0.05
     feather
    -0.05
    æĦıæĢĿ表示
    -0.05
    Normalize
    -0.05
    æĪijä»Ĭ天
    -0.05
    POSITIVE LOGITS
    çŃĭ
    0.07
    åį¸
    0.06
    å¯Ĵ
    0.06
    ench
    0.05
    å³»
    0.05
    ibli
    0.05
    åĢ©
    0.05
    æĺ¼
    0.05
    岸
    0.05
     kho
    0.05
    Activations Density 0.076%

    No Known Activations