© 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. 19284
    Prev
    Next
    INDEX
    Explanations

    averted eyes, head down, website 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
    -contained
    -0.06
    å°¹
    -0.06
    éĢļ天
    -0.05
    tele
    -0.05
    alap
    -0.05
    åľ¨éĤ£éĩĮ
    -0.05
    é¡»åľ¨
    -0.05
    é¦
    -0.05
    人们çļĦ
    -0.05
     Investor
    -0.05
    POSITIVE LOGITS
    YS
    0.06
    bach
    0.06
    uyo
    0.06
    imony
    0.06
    uc
    0.05
    æİ¨è¿Ľä¼ļ
    0.05
    utang
    0.05
    ugi
    0.05
    hand
    0.05
    itz
    0.05
    Activations Density 0.001%

    No Known Activations