© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20464
    Prev
    Next
    INDEX
    Explanations

    democratic and labour party politics

    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
    aber
    -0.05
     rig
    -0.05
     luc
    -0.05
    æķµ
    -0.05
    æĻ¯
    -0.05
    aimer
    -0.05
     doch
    -0.05
    íĪ¬
    -0.05
    สิ
    -0.05
     Theatre
    -0.05
    POSITIVE LOGITS
    ÑĢобÑĸ
    0.07
    ä¸įè°Ī
    0.07
    ãģıãģłãģķãģĦãģŃ
    0.06
    æľĢä½³
    0.06
     bureaucr
    0.06
    è¿Ļä¸Ģ次çļĦ
    0.06
    ä¸į说
    0.06
    лин
    0.06
    çĶ³è¯·æĿ¡ä»¶
    0.06
    óta
    0.06
    Activations Density 0.033%

    No Known Activations