© 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. 22450
    Prev
    Next
    INDEX
    Explanations

    calling out or beckoning

    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
    å¥ĩèij©
    -0.07
    reek
    -0.07
     hell
    -0.06
    æĬµ
    -0.06
    .appspot
    -0.06
    åħ¬åı¸åıĬ
    -0.06
    Deb
    -0.06
    utile
    -0.06
    ãģĴãģŁ
    -0.05
     introdu
    -0.05
    POSITIVE LOGITS
     Journals
    0.05
     certain
    0.05
    riere
    0.05
     conclude
    0.05
    americ
    0.05
     опÑĢеделеннÑĭе
    0.05
    aliz
    0.05
    åħ¼æĢ»ç»ıçIJĨ
    0.05
    rians
    0.05
     concludes
    0.05
    Activations Density 0.005%

    No Known Activations