© 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. 19502
    Prev
    Next
    INDEX
    Explanations

    days and times

    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
    ey
    -0.06
    lab
    -0.06
     jour
    -0.05
     it
    -0.05
    änd
    -0.05
    æīĢæľª
    -0.05
    éĩĩçĶ¨
    -0.05
    å°±éĤ£ä¹Ī
    -0.05
    oz
    -0.05
     lab
    -0.05
    POSITIVE LOGITS
    teki
    0.06
    bie
    0.06
     emergência
    0.06
     gier
    0.06
    Äįni
    0.06
    å¾Īæľī
    0.06
    è¡į
    0.05
    agers
    0.05
    imei
    0.05
    没éĹ®é¢ĺ
    0.05
    Activations Density 0.019%

    No Known Activations