© 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. 22268
    Prev
    Next
    INDEX
    Explanations

    periods of the day and time

    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
    ilda
    -0.08
    ulu
    -0.07
    åIJĪãģĦ
    -0.06
     afar
    -0.06
    å¯ĦäºĪ
    -0.06
    عاÙĦ
    -0.06
    æİ¥åıĹæ²»çĸĹ
    -0.06
    aler
    -0.06
    æĶ¿æ²»å±Ģ
    -0.06
    vc
    -0.05
    POSITIVE LOGITS
    Įĵ
    0.05
     gelungen
    0.05
     poly
    0.05
    ç¼®
    0.05
    æĻĵ
    0.05
     Commons
    0.05
     nighttime
    0.05
    umbed
    0.05
    å¤ľ
    0.05
    onym
    0.05
    Activations Density 0.004%

    No Known Activations