© 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. 16782
    Prev
    Next
    INDEX
    Explanations

    file or installation instructions

    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
    raq
    -0.06
    arah
    -0.06
    QUIRE
    -0.06
     поÑģÑĤа
    -0.06
    ±ħ
    -0.06
    کاÙĨ
    -0.06
     ÅŁÃ¶yle
    -0.06
    ucid
    -0.06
    piring
    -0.06
    稳å®ļæĢ§åĴĮ
    -0.06
    POSITIVE LOGITS
    nb
    0.05
     necessarily
    0.05
    æĺ¯çľŁçļĦ
    0.05
    ↵     ↵
    0.05
    ä¸į
    0.05
    è¯Ĺ
    0.05
    بطة
    0.05
    å¼ı
    0.05
     inception
    0.04
    è¯
    0.04
    Activations Density 0.002%

    No Known Activations