© 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. 16673
    Prev
    Next
    INDEX
    Explanations

    second derivative

    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
     leading
    -0.06
    leading
    -0.06
    ধ
    -0.05
    以ä¸ĭåĩłçĤ¹
    -0.05
    ÙĩÙĨ
    -0.05
     máºŃt
    -0.05
    Im
    -0.05
     possibly
    -0.05
     Den
    -0.05
    '
    -0.05
    POSITIVE LOGITS
    IData
    0.06
    leftright
    0.06
    åı¯éĿł
    0.06
     $($
    0.06
    raries
    0.06
    ä½ı
    0.06
    åıĤåĬłäºĨä¼ļè®®
    0.06
    ARES
    0.06
     Podesta
    0.06
    rez
    0.06
    Activations Density 0.001%

    No Known Activations