© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20878
    Prev
    Next
    INDEX
    Explanations

    CSS selectors

    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
    erville
    -0.07
     underneath
    -0.06
    ÃŃs
    -0.06
    å¤Ł
    -0.06
    olo
    -0.06
    æł¹æľ¬æ²¡
    -0.06
    иÑħ
    -0.05
    交æµģçļĦ
    -0.05
    å®ŀå¹²
    -0.05
    udin
    -0.05
    POSITIVE LOGITS
     partial
    0.06
    partial
    0.06
    zell
    0.05
    seh
    0.05
    ìŀ¥ìĿ´
    0.05
    ä¹ĭéķ¿
    0.05
    è±ļ
    0.05
     dearly
    0.05
    éŨçļĦ
    0.05
    enet
    0.05
    Activations Density 0.011%

    No Known Activations