© 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. 16600
    Prev
    Next
    INDEX
    Explanations

    resources

    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
    elled
    -0.07
    alah
    -0.06
    urban
    -0.06
    lenen
    -0.06
    alous
    -0.05
    å¾®å°ı
    -0.05
    edik
    -0.05
    -min
    -0.05
    ornos
    -0.05
    为åħ¶
    -0.05
    POSITIVE LOGITS
    ÄĻk
    0.06
    åĤį
    0.06
    venuti
    0.06
     unle
    0.05
    رÙĬع
    0.05
    tep
    0.05
     formulario
    0.05
    oth
    0.05
     pewnoÅĽciÄħ
    0.05
    ULK
    0.05
    Activations Density 0.005%

    No Known Activations