© 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. 20462
    Prev
    Next
    INDEX
    Explanations

    required fields

    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
    ä¹Łå°±æĺ¯è¯´
    -0.07
    å°±æĺ¯è¯´
    -0.06
    aller
    -0.06
    ä¹Łå°±æĺ¯èªª
    -0.06
     chá»ijt
    -0.06
    ailable
    -0.06
    annen
    -0.06
     ê¼
    -0.06
    ê¼
    -0.05
    á»ijt
    -0.05
    POSITIVE LOGITS
    å¨ģåĬĽ
    0.06
    ×¢×Ļ×Ŀ
    0.06
    æĽľ
    0.05
    nat
    0.05
     potent
    0.05
    eira
    0.05
    ijat
    0.05
    Mbps
    0.05
    ensation
    0.05
    æķĪèĥ½
    0.05
    Activations Density 0.003%

    No Known Activations