© 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. 16603
    Prev
    Next
    INDEX
    Explanations

    determine the

    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
    udu
    -0.06
    ÙĪر
    -0.06
    uki
    -0.06
    ukum
    -0.06
    åĵ¥çļĦ
    -0.06
    bul
    -0.06
    uku
    -0.06
    ivu
    -0.05
    å®ļä¹ī为
    -0.05
    ubu
    -0.05
    POSITIVE LOGITS
    Fcn
    0.06
    å®ļçļĦ
    0.06
    å©Ģ
    0.06
    asing
    0.06
    sWith
    0.05
    Ñħов
    0.05
    èĩ´çļĦ
    0.05
     Broncos
    0.05
    td
    0.05
    itures
    0.05
    Activations Density 0.020%

    No Known Activations