© 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. 19111
    Prev
    Next
    INDEX
    Explanations

    decreasing, descending, or rtl order

    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
    åĤ»çĵľ
    -0.06
    æĸ¹åIJij
    -0.06
    ile
    -0.05
    ingo
    -0.05
    ester
    -0.05
    front
    -0.05
    ben
    -0.05
    ina
    -0.05
    acob
    -0.05
    æĺ¥æĿ¥
    -0.05
    POSITIVE LOGITS
    æĹłéĺ»
    0.07
     decad
    0.06
    é£Ļ
    0.06
    åIJĥèĤī
    0.06
    æĹłåīį
    0.06
     vmax
    0.06
    èche
    0.06
    ç´§éļı
    0.06
    agni
    0.06
     perc
    0.06
    Activations Density 0.004%

    No Known Activations