© 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. 21404
    Prev
    Next
    INDEX
    Explanations

    variables replaced or filled

    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
    меÑĤим
    -0.06
    ksz
    -0.06
    ÏĦÎŃÏģα
    -0.06
     ë°ĸìĹIJ
    -0.06
    IGE
    -0.06
    vasti
    -0.06
    uco
    -0.06
    wod
    -0.05
    ê»ĺ
    -0.05
    (models
    -0.05
    POSITIVE LOGITS
    å®ŀçļĦ
    0.06
     filled
    0.06
    æIJŀ
    0.05
    æ´½
    0.05
    æĽ¿æį¢
    0.05
    次çļĦ
    0.05
    å®ŀ
    0.05
    åıĸèĢĮ代ä¹ĭ
    0.05
     contents
    0.05
     Snyder
    0.05
    Activations Density 0.013%

    No Known Activations