© 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. 16901
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     underlying
    -0.06
    ogn
    -0.06
    obile
    -0.05
    满äºĨ
    -0.05
     rather
    -0.05
    æ¸ħæ¥ļ
    -0.05
    éķ¿æĮī
    -0.05
     dig
    -0.05
    WISE
    -0.05
     limited
    -0.04
    POSITIVE LOGITS
    aci
    0.06
     reprises
    0.06
    _Of
    0.06
    æĹ¥ä»¥æĿ¥
    0.06
    éĿ¡
    0.06
    adis
    0.06
    å§ĭç»Ī以
    0.06
    åĮ¿åIJįçĶ¨æĪ·
    0.06
    _POS
    0.06
    ciel
    0.06
    Activations Density 0.000%

    No Known Activations