© 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. 19788
    Prev
    Next
    INDEX
    Explanations

    include

    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
    è¯Ń
    -0.07
    èijĹ
    -0.06
    æĥħ
    -0.06
    éĿ©
    -0.06
     tagged
    -0.05
    ê¸Ī
    -0.05
     grant
    -0.05
     granted
    -0.05
    åĪ¶
    -0.05
    æĸĹ
    -0.05
    POSITIVE LOGITS
    bose
    0.06
    èIJ½ãģ¨ãģĹ
    0.06
     diker
    0.06
    ä¸ŃåĽ½äººçļĦ
    0.06
    ãģĵãģ¨ãģ«ãģªãĤĭ
    0.06
     Alme
    0.06
    åľ¨ä¸º
    0.06
    縣éķ·
    0.06
    æijĩ头
    0.06
    secondary
    0.06
    Activations Density 0.013%

    No Known Activations