© 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. 19727
    Prev
    Next
    INDEX
    Explanations

    to watch here

    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
    pe
    -0.05
    åıijå±ķæ½ľåĬĽ
    -0.05
     el
    -0.05
    ivy
    -0.05
    è¿ŁéĴĿ
    -0.05
    æIJħ
    -0.05
    大åIJĥä¸ĢæĥĬ
    -0.05
     hor
    -0.05
    redit
    -0.05
    dea
    -0.05
    POSITIVE LOGITS
    ukk
    0.07
    arness
    0.07
    apo
    0.06
     Pug
    0.06
    æĺ¾
    0.06
    opard
    0.06
    apul
    0.06
    bourg
    0.06
    æIJ¬è¿IJ
    0.06
     cómoda
    0.06
    Activations Density 0.003%

    No Known Activations