© 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. 19217
    Prev
    Next
    INDEX
    Explanations

    digits and calculations

    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
    æīĭçļĦ
    -0.05
    มืà¸Ń
    -0.05
    çĶ¨ä¸Ģ个
    -0.05
    ä½łçŁ¥éģĵåIJĹ
    -0.05
    说åIJ§
    -0.05
    æīĭãģ§
    -0.05
     Insomma
    -0.05
    roll
    -0.05
    rosse
    -0.05
    rovers
    -0.05
    POSITIVE LOGITS
    omo
    0.06
    ÃŃdos
    0.06
    =item
    0.06
    ä¸įä¹±
    0.06
    æŃ¤èµ·
    0.06
    iped
    0.06
    ijin
    0.05
    cko
    0.05
     Chromium
    0.05
     fatally
    0.05
    Activations Density 0.022%

    No Known Activations