© 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. 18551
    Prev
    Next
    INDEX
    Explanations

    head of state titles

    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
    à¸ķิà¸Ķ
    -0.06
    egna
    -0.06
    碧
    -0.06
    第ä¸Ģ次
    -0.05
    ä¸Ģ次çļĦ
    -0.05
    å±ķ
    -0.05
     igjen
    -0.05
    ļ
    -0.05
    æĹ¥ä»¥æĿ¥
    -0.05
     once
    -0.05
    POSITIVE LOGITS
    èµĭäºĪ
    0.06
    深水
    0.06
    踩è¿ĩ
    0.06
     Coy
    0.06
    åĩĿè¡Ģ
    0.05
     profonditÃł
    0.05
    è¡Ģåŀĭ
    0.05
    sept
    0.05
    èĢĮä½ľä¸º
    0.05
     ÑĦоÑĢм
    0.05
    Activations Density 0.009%

    No Known Activations