© 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. 22548
    Prev
    Next
    INDEX
    Explanations

    ... what

    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
     bothering
    -0.06
    usun
    -0.05
    uis
    -0.05
    æĭŁ
    -0.05
    Õ¡Õ¶
    -0.05
    ä¸ĵæľī
    -0.05
    Òĵ
    -0.05
    æºIJèĩª
    -0.05
    åıĸåĨ³
    -0.05
    ulon
    -0.05
    POSITIVE LOGITS
     sint
    0.06
    istry
    0.06
    ught
    0.06
    engg
    0.06
    λί
    0.05
    meros
    0.05
    istica
    0.05
    å°§
    0.05
     PENG
    0.05
     Yep
    0.05
    Activations Density 0.007%

    No Known Activations