© 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. 22412
    Prev
    Next
    INDEX
    Explanations

    lists of things

    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
    Ñı
    -0.06
    logen
    -0.06
    éĶĻ误çļĦæĺ¯
    -0.05
    ä¸Ĭåĵģ
    -0.05
    ound
    -0.05
    æĪĸ使çĶ¨
    -0.05
    åį³åı¯
    -0.05
    ered
    -0.05
    roller
    -0.05
    æĪIJç«ĭçļĦ
    -0.05
    POSITIVE LOGITS
     abuses
    0.06
     abuse
    0.06
    доб
    0.06
    ষà§įà¦ł
    0.06
    ambi
    0.06
    éĢĤ
    0.05
    ieza
    0.05
     inú
    0.05
     Hath
    0.05
    æĶ¤
    0.05
    Activations Density 0.036%

    No Known Activations