© 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. 22408
    Prev
    Next
    INDEX
    Explanations

    rubber products and components

    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
    讼
    -0.06
    wajibkan
    -0.06
    aglia
    -0.06
    uring
    -0.06
    mites
    -0.06
    æĮijçľī
    -0.06
     Alta
    -0.06
    елÑı
    -0.06
    culares
    -0.06
    åħ¶äºº
    -0.06
    POSITIVE LOGITS
     Rubber
    0.09
     rubber
    0.09
    æ©¡èĥ¶
    0.08
    er
    0.08
    æ©¡
    0.06
    èķī
    0.06
     pad
    0.06
    clipse
    0.06
    ยาà¸ĩ
    0.06
    Rub
    0.06
    Activations Density 0.012%

    No Known Activations