© 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. 16627
    Prev
    Next
    INDEX
    Explanations

    knowledge and understanding

    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
    reads
    -0.06
    adam
    -0.06
    forth
    -0.06
    vers
    -0.06
    illar
    -0.06
    uppy
    -0.06
    mitglied
    -0.06
    pics
    -0.06
    Leggi
    -0.06
    verfahren
    -0.06
    POSITIVE LOGITS
    æĸĻ
    0.06
    æĸĻçļĦ
    0.06
    éĥ¨
    0.06
    ä½IJ
    0.05
     mis
    0.05
     Bor
    0.05
    åįĴ
    0.05
    æľīä¸Ģ份
    0.05
    ancellable
    0.05
     Pul
    0.05
    Activations Density 0.037%

    No Known Activations