© 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. 22605
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms

    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
    ,
    -0.06
    -
    -0.05
    以
    -0.05
    å¤ļ
    -0.05
     inters
    -0.05
    -0.04
    ಷ
    -0.04
    are
    -0.04
     ^
    -0.04
    çļ®
    -0.04
    POSITIVE LOGITS
    æŀ¶è®¾
    0.07
    éĨ¤
    0.07
    allel
    0.07
    eggi
    0.07
    klaim
    0.07
    æĦŁåįģ足
    0.07
    ÄĽÅ¾
    0.07
    次äºİ
    0.07
    JKLMNOP
    0.06
     нежела
    0.06
    Activations Density 0.115%

    No Known Activations