© 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. 22063
    Prev
    Next
    INDEX
    Explanations

    historic places and objects

    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
     rez
    -0.06
    ông
    -0.05
     Schwartz
    -0.05
    å±ij
    -0.05
     hÃŃ
    -0.05
    èŀį
    -0.05
    éĻĦ
    -0.05
     Sett
    -0.05
    æĹłè§Ĩ
    -0.05
    shelf
    -0.05
    POSITIVE LOGITS
     traces
    0.06
    çĹķ迹
    0.06
     réalise
    0.06
    пиÑĤ
    0.06
    çļĦçĹķ迹
    0.06
     markings
    0.06
     trace
    0.06
    éĢ¼çľŁçļĦ
    0.06
    è¸IJ
    0.06
    uste
    0.06
    Activations Density 0.035%

    No Known Activations