© 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. 19561
    Prev
    Next
    INDEX
    Explanations

    changing color of property

    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
     true
    -0.06
     tre
    -0.06
     Tre
    -0.05
     try
    -0.05
     tried
    -0.05
    Tre
    -0.05
     SA
    -0.05
     Th
    -0.05
    æŀ¶ä¸Ĭ
    -0.05
     hash
    -0.04
    POSITIVE LOGITS
     indirectly
    0.06
    è¿ŀ带
    0.06
    æį²
    0.06
    -Cs
    0.06
     впеÑĩаÑĤление
    0.06
    ×ķ׾×Ķ
    0.06
    лик
    0.06
     многое
    0.06
     Raya
    0.06
    inka
    0.06
    Activations Density 0.040%

    No Known Activations