© 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. 22362
    Prev
    Next
    INDEX
    Explanations

    Copyright statements

    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
    å°¼æĸ¯
    -0.05
    åĶ¬
    -0.05
    åŃ¦å¼Ł
    -0.05
    æĤĶ
    -0.05
    ç¾Ķ
    -0.05
    çal
    -0.05
     Tos
    -0.05
    æĪ
    -0.05
    ç»Ĩ
    -0.05
    ucker
    -0.05
    POSITIVE LOGITS
     canti
    0.06
    edd
    0.06
    éns
    0.06
     efetu
    0.06
    .Exists
    0.05
    bbc
    0.05
    aglia
    0.05
    壹
    0.05
    apur
    0.05
    æĪIJ为ä¸Ģç§į
    0.05
    Activations Density 0.004%

    No Known Activations