© 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. 16810
    Prev
    Next
    INDEX
    Explanations

    keep running

    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
    ariado
    -0.06
    çĶ¨å¾®ä¿¡
    -0.06
    Jvm
    -0.06
    upan
    -0.06
    icano
    -0.06
    uis
    -0.06
    å±ķåĮº
    -0.06
    æĥľ
    -0.06
     ëĭ
    -0.06
    å¨ģ
    -0.06
    POSITIVE LOGITS
     un
    0.06
    空èĻļ
    0.05
    ä¸įå¹³
    0.05
    ande
    0.05
    åĩŃ空
    0.05
     empty
    0.05
     blind
    0.05
    oku
    0.05
    laf
    0.05
     абÑģолÑİÑĤно
    0.05
    Activations Density 0.008%

    No Known Activations