© 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. 19433
    Prev
    Next
    INDEX
    Explanations

    used in

    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
    ey
    -0.07
    is
    -0.06
    è°ģ家
    -0.06
    EP
    -0.06
    ore
    -0.06
    egl
    -0.06
     rien
    -0.06
    人åıĹ伤
    -0.05
    ÙĬر
    -0.05
    .Comparator
    -0.05
    POSITIVE LOGITS
    sstr
    0.06
    fully
    0.06
    encontre
    0.06
    ampire
    0.06
    à¹Ħร
    0.06
    /out
    0.06
     Gingrich
    0.06
    çļĦãģ«
    0.05
    wend
    0.05
    è¿Ľä¸ĢæŃ¥åĬłå¤§
    0.05
    Activations Density 0.028%

    No Known Activations