© 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. 17422
    Prev
    Next
    INDEX
    Explanations

    end date or 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
    antar
    -0.06
    mente
    -0.06
    çļĦæľĭåıĭåı¯ä»¥
    -0.06
    ually
    -0.06
    ally
    -0.06
    Ant
    -0.06
    icio
    -0.05
    atters
    -0.05
    æ´ŀ
    -0.05
    åħ¶ä»ĸæĸ¹å¼ı
    -0.05
    POSITIVE LOGITS
    emn
    0.06
    ãģĭãģķ
    0.06
    ubb
    0.06
    arrow
    0.06
    SHIFT
    0.05
    度è¿ĩ
    0.05
    ä¸įå¾ĹäºĨ
    0.05
     overl
    0.05
    ogan
    0.05
    headed
    0.05
    Activations Density 0.008%

    No Known Activations