© 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. 22471
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
    spur
    -0.06
    .ng
    -0.06
     vali
    -0.05
    äºĭ
    -0.05
    sti
    -0.05
    emit
    -0.05
    registr
    -0.05
    åľ¨æŁIJ
    -0.05
    illin
    -0.05
    ä¸įæŃ»
    -0.05
    POSITIVE LOGITS
     vision
    0.05
     Ive
    0.05
     Sach
    0.05
    liwe
    0.05
    _iface
    0.05
    vider
    0.05
    rach
    0.05
     jointly
    0.05
    ron
    0.05
    ড়া
    0.05
    Activations Density 0.004%

    No Known Activations