© 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. 17440
    Prev
    Next
    INDEX
    Explanations

    variable assignments with symbols

    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
    ondo
    -0.06
    åĽĽé¡¹
    -0.06
    äºĨæĪijçļĦ
    -0.06
    actly
    -0.05
    usat
    -0.05
    ond
    -0.05
    éĺª
    -0.05
    <>
    -0.05
    å·
    -0.05
    ocratic
    -0.05
    POSITIVE LOGITS
    antar
    0.06
    åłĤ
    0.06
    ÑĮеÑĢ
    0.06
    kerne
    0.06
     modified
    0.05
    ulich
    0.05
    æľīæľºä¼ļ
    0.05
     mark
    0.05
    Alter
    0.05
    ÙĤدر
    0.05
    Activations Density 0.038%

    No Known Activations