© 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. 18654
    Prev
    Next
    INDEX
    Explanations

    ignition and combustion

    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
     dưỡng
    -0.07
    åĽłä¸ºåıªæľī
    -0.06
    halter
    -0.06
     powered
    -0.06
    马æĭī
    -0.05
    eru
    -0.05
    åºķ座
    -0.05
    åĽłä¸ºè¿Ļ
    -0.05
    artigen
    -0.05
    bury
    -0.05
    POSITIVE LOGITS
    ä¸įè¿ĩ
    0.06
    ropp
    0.06
    ıc
    0.05
    upaya
    0.05
    emon
    0.05
    ÛĮÙĩ
    0.05
    à¸Ľà¸£à¸°à¸ªà¸ĩà¸Ħà¹Į
    0.05
    ÑģоÑĢ
    0.05
    åłĤåłĤ
    0.05
    remark
    0.05
    Activations Density 0.001%

    No Known Activations