© 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. 18813
    Prev
    Next
    INDEX
    Explanations

    ortho-

    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
    空èĻļ
    -0.07
    URE
    -0.06
    ures
    -0.06
    urer
    -0.06
    gica
    -0.06
    å¾Ĺæ°´
    -0.06
    andangan
    -0.06
    Chess
    -0.06
    大大å°ı
    -0.06
    æģ¯çļĦ
    -0.06
    POSITIVE LOGITS
    pend
    0.05
    L
    0.05
    è¡ĮæĶ¿
    0.05
    ä¹Łæĺ¯æľĢ
    0.05
    alis
    0.05
    both
    0.05
     both
    0.05
    御
    0.05
    çºł
    0.05
    ç¼ķ
    0.05
    Activations Density 0.018%

    No Known Activations