© 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. 19328
    Prev
    Next
    INDEX
    Explanations

    left ventricular, lysosomes, physical health, overall health, internal region, European countries, contralateral hemisphere

    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
    acement
    -0.06
    è½½
    -0.06
    veda
    -0.05
    ucher
    -0.05
    vera
    -0.05
    aversal
    -0.05
    udad
    -0.05
    ver
    -0.05
    voc
    -0.05
    Ùģت
    -0.05
    POSITIVE LOGITS
    éĹ´æİ¥
    0.07
    Proxy
    0.06
     indirect
    0.06
    è¿ŀ带
    0.06
    åįıåĬŀ
    0.06
    åħ³èģĶä¼ģä¸ļ
    0.06
    åĢŁçĶ¨
    0.06
    -proxy
    0.06
    proxy
    0.06
     indirectly
    0.06
    Activations Density 0.119%

    No Known Activations