© 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. 19799
    Prev
    Next
    INDEX
    Explanations

    title case column names

    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
    yor
    -0.06
    LOB
    -0.06
    ä¸Ńéĸĵ
    -0.06
    .wrap
    -0.05
     relation
    -0.05
    æĦŁåıĹåĴĮ
    -0.05
    èħĨ
    -0.05
    延éķ·
    -0.05
     attempts
    -0.05
    quin
    -0.05
    POSITIVE LOGITS
    defs
    0.07
    è¿Ļä¹Ī好
    0.05
    å®ŀ
    0.05
    ç»ı
    0.05
    Inc
    0.05
    åĵĪéĩĮ
    0.05
    顺
    0.05
    odat
    0.05
    '^$',
    0.05
    éªĹå±Ģ
    0.05
    Activations Density 0.002%

    No Known Activations