© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18132
    Prev
    Next
    INDEX
    Explanations

    cosmic horror and relativism

    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
    Not in Any Lists

    No Comments

    Negative Logits
     controvers
    -0.06
     viva
    -0.06
    bre
    -0.06
    ä¸įä¸Ģ
    -0.05
     кÑĢи
    -0.05
    ä¼łçļĦ
    -0.05
    å¡ij
    -0.05
     saga
    -0.05
    ative
    -0.05
    bie
    -0.05
    POSITIVE LOGITS
     nihil
    0.06
    ä¸ĭæ²ī
    0.06
    ÄĻk
    0.06
    Ïģν
    0.06
    éĻ¢æīĢ
    0.06
    æīĵãģ¡
    0.06
     беÑĤ
    0.06
     Provinc
    0.05
    елÑĮ
    0.05
    éĺ¿æ£®
    0.05
    Activations Density 0.018%

    No Known Activations