© 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. 21674
    Prev
    Next
    INDEX
    Explanations

    chemical process intermediates

    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
    çļĦè¦ģ
    -0.06
    æģIJ
    -0.05
    æijĦ
    -0.05
    æij©çĻ»
    -0.05
    bbbb
    -0.05
    墨
    -0.05
    ç¹³
    -0.05
    igue
    -0.05
    åĬłè½½ä¸Ń
    -0.05
    ÃŃg
    -0.05
    POSITIVE LOGITS
    åľŁåľ°åĪ©çĶ¨
    0.06
    avors
    0.05
    ometown
    0.05
    æĻ¯è±¡
    0.05
     Crowley
    0.05
    ãģªãģı
    0.05
    iras
    0.05
     Academ
    0.05
    oser
    0.05
     Wales
    0.05
    Activations Density 0.025%

    No Known Activations