© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22455
    Prev
    Next
    INDEX
    Explanations

    servers, dates, and times

    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
    Negative Logits
    段
    -0.05
     Hen
    -0.05
    ·
    -0.05
    rav
    -0.05
    追
    -0.05
    æĻ¯
    -0.05
    ecem
    -0.04
    åįĩ
    -0.04
     impre
    -0.04
    ä½į
    -0.04
    POSITIVE LOGITS
    idet
    0.07
    acr
    0.07
    printStats
    0.07
    ÙĪÙĬات
    0.06
    oeff
    0.06
    iems
    0.06
    åĻ
    0.06
    undet
    0.06
    iefs
    0.06
    boundary
    0.06
    Activations Density 0.005%

    No Known Activations