© 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. 20911
    Prev
    Next
    INDEX
    Explanations

    physical controls to be activated

    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
    operative
    -0.06
    ä¸įæŃ£
    -0.05
    èģĶåIJĪä¼ļ
    -0.05
    orative
    -0.05
    ouble
    -0.05
    åŀĽ
    -0.05
    ãģķãĤĵ
    -0.05
    临
    -0.05
    opoly
    -0.05
    èĩ¨
    -0.05
    POSITIVE LOGITS
     everything
    0.06
    åıĺæĽ´åIJİ
    0.06
    è¸ı
    0.05
    ivet
    0.05
    åĸĤ
    0.05
     continuidade
    0.05
    æĭįæīĭ
    0.05
    Ñģило
    0.05
    gestaltung
    0.05
    å¿«èĬĤå¥ı
    0.05
    Activations Density 0.013%

    No Known Activations