© 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. 19643
    Prev
    Next
    INDEX
    Explanations

    passing through

    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
     perju
    -0.06
    åľ¨éĤ£ä¸ª
    -0.05
    æºĸ
    -0.05
    ul
    -0.05
     KER
    -0.05
     soi
    -0.05
    è½»æĺĵ
    -0.05
    æĺ¯ä»Ģä¹Īåij¢
    -0.05
    æħ£
    -0.05
    aint
    -0.05
    POSITIVE LOGITS
    éĵŃ
    0.06
    为åħ¶
    0.06
    áĥIJáĥķ
    0.06
    tagon
    0.06
    å¿ĥèĦı
    0.05
    ÏĦÎŃÏģ
    0.05
    åĽłåħ¶
    0.05
    éĬĺ
    0.05
    central
    0.05
    leur
    0.05
    Activations Density 0.035%

    No Known Activations