© 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. 19373
    Prev
    Next
    INDEX
    Explanations

    below

    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
    Ø©
    -0.07
    æī©å±ķèµĦæĸĻ
    -0.07
    หà¸Ļ
    -0.06
    eger
    -0.06
    emblée
    -0.06
    æĿ¥éĻ¢
    -0.06
    ÑĩеÑĢед
    -0.06
    缸åħ³éĵ¾æİ¥
    -0.06
     hòn
    -0.06
     inilah
    -0.06
    POSITIVE LOGITS
    jenigen
    0.05
    zie
    0.05
    rete
    0.05
    ative
    0.05
    Ø£ÙĬ
    0.05
    ضÙĬØ©
    0.05
    æħĭ
    0.05
    vor
    0.05
    æĬĵä½ıäºĨ
    0.05
    ellen
    0.05
    Activations Density 0.018%

    No Known Activations