© 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. 18774
    Prev
    Next
    INDEX
    Explanations

    user identifier or data field

    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
    лаÑĤ
    -0.07
    uve
    -0.06
    æ°´æĺ¯
    -0.06
    æĮĩ导ä¸ĭ
    -0.06
     "`
    -0.06
    ptest
    -0.06
     drauf
    -0.06
    okit
    -0.06
    è¨Ģä¹ĭ
    -0.06
    羣çIJĨ
    -0.05
    POSITIVE LOGITS
     ra
    0.06
    Ûģ
    0.05
    çªĦ
    0.05
    į
    0.05
     arz
    0.05
     pa
    0.05
    à¹Į
    0.05
    褥
    0.05
    uelas
    0.05
    меÑĩа
    0.05
    Activations Density 0.017%

    No Known Activations