© 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. 20116
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
    umpt
    -0.06
    szyscy
    -0.06
     numerical
    -0.06
     استعداد
    -0.06
     serviced
    -0.06
    éĥ½æľīåı¯èĥ½
    -0.06
    Runner
    -0.06
    aser
    -0.06
    ä¸Ĭè¡Į
    -0.06
    æľªå°½
    -0.05
    POSITIVE LOGITS
    åıĸèĩª
    0.05
    wort
    0.05
    æķĪåĬĽ
    0.05
    activ
    0.05
    fix
    0.05
    æķĪæŀľ
    0.05
    å±ķ示åĩº
    0.05
     berw
    0.05
    èĤĨ
    0.05
    à¹īา
    0.05
    Activations Density 0.050%

    No Known Activations